© 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. 1-RES-JB
    11. 13923
    Prev
    Next
    INDEX
    Explanations

    commands or instructions indicating a required action

    oai_token-act-pair · gpt-3.5-turbo

    the word "always" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SG
    -0.85
    åĤ
    -0.78
    LU
    -0.77
    IDA
    -0.76
    href
    -0.75
    SPEC
    -0.74
    LAN
    -0.73
    RD
    -0.72
    dyl
    -0.70
    DEM
    -0.69
    POSITIVE LOGITS
    entimes
    1.09
     comma
    0.77
     advisable
    0.76
    Always
    0.75
     Always
    0.75
     vigilance
    0.74
     iod
    0.73
     regener
    0.71
    otin
    0.70
     underestimate
    0.70
    Activations Density 0.005%

    No Known Activations