© 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. 17074
    Prev
    Next
    INDEX
    Explanations

    conjunctions or phrases containing symbols like unicode arrow symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used for emphasis

    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
    ...]
    -0.66
    ãĤ©
    -0.65
     guiActiveUnfocused
    -0.64
     Ended
    -0.64
    pei
    -0.64
     )))
    -0.64
     Joined
    -0.62
    enta
    -0.62
     Seconds
    -0.61
    ocobo
    -0.60
    POSITIVE LOGITS
    especially
    1.25
     namely
    1.19
    particularly
    1.15
    albeit
    1.05
     albeit
    1.02
    except
    0.99
    although
    0.96
    they
    0.95
    maybe
    0.95
    until
    0.94
    Activations Density 0.160%

    No Known Activations