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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 529
    Prev
    Next
    INDEX
    Explanations

    text related to historical figures and events

    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
    460
    +0.14
    0.5%
    240
    +0.12
    0.4%
    420
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.14
    0.06
    632
    +0.12
    0.05
    643
    +0.11
    0.04
    Negative Logits
    ufact
    -1.08
    kefeller
    -0.95
    gren
    -0.92
    manship
    -0.92
    senal
    -0.91
    zona
    -0.86
    ongyang
    -0.86
     bottleneck
    -0.85
    mable
    -0.84
     neighb
    -0.84
    POSITIVE LOGITS
    pmwiki
    1.05
    âĨij
    1.01
    References
    0.97
    ][
    0.92
    ].
    0.89
    ...]
    0.88
    Sources
    0.88
    ],"
    0.87
    "]
    0.86
     ]
    0.84
    Activations Density 0.206%

    No Known Activations