© 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. 2-RES-JB
    11. 805
    Prev
    Next
    INDEX
    Explanations

    words related to calculations or math

    oai_token-act-pair · gpt-3.5-turbo

    the syllable "cul" within words

    oai_token-act-pair · gpt-4-turbo

    words related to culture and societal influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.71
     Blaz
    -0.70
     Pilgrim
    -0.68
     Cooke
    -0.63
     ãĤµ
    -0.63
     Franks
    -0.62
     Veterans
    -0.62
     Sheen
    -0.62
     Alph
    -0.62
     Shell
    -0.61
    POSITIVE LOGITS
    cul
    1.24
    ately
    1.08
    ocity
    1.08
    iar
    1.06
    itic
    0.99
    iosity
    0.98
    ision
    0.96
    ators
    0.96
    culation
    0.94
    entric
    0.93
    Activations Density 0.004%

    No Known Activations