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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16277
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific conditions or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    env
    -0.68
    ahime
    -0.61
    duino
    -0.59
    insula
    -0.58
    idon
    -0.57
     PLUS
    -0.55
    arted
    -0.53
     converter
    -0.53
    patch
    -0.52
    comb
    -0.52
    POSITIVE LOGITS
     marginally
    0.99
    ices
    0.85
     insofar
    0.85
     spor
    0.83
    ICES
    0.81
     incidentally
    0.78
    onse
    0.77
    ones
    0.72
     mildly
    0.71
     scratches
    0.68
    Activations Density 0.068%

    No Known Activations