© 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. 0-RES-JB
    11. 16538
    Prev
    Next
    INDEX
    Explanations

    terms related to professional titles and credentials

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    och
    -0.71
    ukong
    -0.66
    ocent
    -0.65
    elled
    -0.64
    ences
    -0.63
    zac
    -0.61
    omas
    -0.61
    ogg
    -0.61
     eldest
    -0.61
     bowl
    -0.59
    POSITIVE LOGITS
     RE
    3.49
    RE
    1.79
     REC
    1.52
     REM
    1.46
     RET
    1.40
     Re
    1.40
     FE
    1.37
     RES
    1.34
     PRE
    1.34
     RI
    1.32
    Activations Density 0.013%

    No Known Activations