Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4479
    Prev
    Next
    INDEX
    Explanations

    information related to economic issues, specifically debt and financial challenges faced by students

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    27
    +0.12
    0.5%
    153
    +0.10
    0.4%
    292
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.24
    27
    +0.10
    0.09
    36
    +0.10
    0.14
    Negative Logits
    codes
    -0.85
    casts
    -0.84
     transcripts
    -0.82
    andals
    -0.81
    mails
    -0.81
    akings
    -0.80
    guards
    -0.80
     inspectors
    -0.80
    ammers
    -0.80
     seals
    -0.79
    POSITIVE LOGITS
     standpoint
    1.22
     perspective
    0.98
     extent
    0.98
     degree
    0.94
     disadvantage
    0.90
     timeframe
    0.88
     footing
    0.87
     basis
    0.87
     range
    0.86
     manner
    0.85
    Activations Density 9.593%

    No Known Activations