© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11700
    Prev
    Next
    INDEX
    Explanations

    instances where the word 'count' or its variations appear in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "count" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.76
    ieties
    -0.76
    insula
    -0.72
    antha
    -0.70
    etheus
    -0.67
     educ
    -0.66
    obar
    -0.64
    ovie
    -0.63
    \\\\\\\\\\\\\\\\
    -0.63
     constitu
    -0.63
    POSITIVE LOGITS
    enance
    2.07
    downs
    0.94
    esses
    0.83
    ere
    0.79
    ENCY
    0.77
    rified
    0.75
    stakes
    0.73
    tops
    0.72
    din
    0.72
    books
    0.71
    Activations Density 0.016%

    No Known Activations