© 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. 11-RES-JB
    6. 9420
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    common phrases related to political action and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subur
    -0.69
    ÃĥÃĤ
    -0.69
    ãĤ¢ãĥ«
    -0.63
    ONSORED
    -0.63
    Ý
    -0.62
    oulos
    -0.62
    ¯¯¯¯¯¯¯¯
    -0.59
    ccording
    -0.59
    sonian
    -0.59
    ischer
    -0.58
    POSITIVE LOGITS
     us
    1.32
     me
    1.21
     them
    1.14
     him
    1.11
     ya
    0.96
     yourselves
    0.94
     you
    0.91
     THEM
    0.91
     thee
    0.88
     yours
    0.87
    Activations Density 0.602%

    No Known Activations