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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13232
    Prev
    Next
    INDEX
    Explanations

    mentions of job positions or roles named "tenure"

    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
    447
    +0.15
    0.8%
    195
    +0.10
    0.5%
    497
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.24
    195
    +0.10
    0.01
    593
    +0.08
    0.05
    Negative Logits
    ortium
    -0.62
    izen
    -0.58
    ocker
    -0.55
    ulsive
    -0.55
    Cart
    -0.53
    Heart
    -0.52
    ulsion
    -0.52
    Import
    -0.52
    afort
    -0.51
    aucuses
    -0.50
    POSITIVE LOGITS
     tenure
    0.74
    aciously
    0.59
    min
    0.57
     reign
    0.56
    days
    0.54
     terminated
    0.53
    entimes
    0.52
    ttes
    0.51
    acious
    0.50
    lasses
    0.50
    Activations Density 8.629%

    No Known Activations