© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8077
    Prev
    Next
    INDEX
    Explanations

    mentions of covert operations or secretive activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or actions relevant to politics and current affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÂŃ
    -1.24
     â̦
    -1.10
     ÂŃ
    -1.06
    –
    -1.00
    â̳
    -1.00
    .–
    -0.99
     â̦"
    -0.99
    â̦â̦â̦â̦
    -0.94
    â̲
    -0.93
    â̦)
    -0.92
    POSITIVE LOGITS
     -
    1.91
     �
    1.32
    "...
    1.17
     ``
    1.08
     ----------------------------------------------------------------
    1.03
    ''.
    1.03
    ``
    1.01
    BBC
    0.96
    �
    0.94
    ...
    0.92
    Activations Density 0.156%

    No Known Activations