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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 4541
    Prev
    Next
    INDEX
    Explanations

    references to physical locations, specifically mentioning the ground

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    649
    +0.16
    0.6%
    288
    +0.14
    0.5%
    422
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.16
    0.06
    298
    +0.14
    0.06
    677
    +0.14
    0.06
    Negative Logits
    ansen
    -0.99
    ļéĨĴ
    -0.98
    士
    -0.97
    xit
    -0.95
    avorite
    -0.92
    vantage
    -0.92
     caut
    -0.89
    ocide
    -0.87
    Whit
    -0.86
    regon
    -0.86
    POSITIVE LOGITS
     floor
    1.08
    fare
    1.08
    waves
    1.05
     footing
    0.96
    floor
    0.95
    raid
    0.88
    plane
    0.85
     leash
    0.85
     periphery
    0.85
     hunger
    0.84
    Activations Density 0.671%

    No Known Activations