© 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. 11-RES-JB
    11. 22668
    Prev
    Next
    INDEX
    Explanations

    proper nouns or entities mentioned in a rather technical or formal context

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and definitive statements

    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
    Enlarge
    -0.60
    prising
    -0.54
    Had
    -0.53
    attering
    -0.52
    paio
    -0.52
    Marginal
    -0.52
    awed
    -0.51
    ences
    -0.51
    790
    -0.50
    wana
    -0.50
    POSITIVE LOGITS
     is
    1.38
     Is
    1.06
     are
    1.05
     IS
    1.00
    is
    0.95
     isn
    0.95
     was
    0.85
     Are
    0.84
     ARE
    0.84
     iss
    0.84
    Activations Density 0.398%

    No Known Activations