© 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. 4143
    Prev
    Next
    INDEX
    Explanations

    the word "standby."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to standby positions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     MAT
    -0.74
     VAL
    -0.73
    UES
    -0.70
     Dw
    -0.68
     Ref
    -0.67
     Orb
    -0.67
    Ö
    -0.66
     EV
    -0.65
    DS
    -0.65
     HE
    -0.65
    POSITIVE LOGITS
    uckland
    0.91
    ulhu
    0.89
    ingly
    0.88
    uminati
    0.85
    agascar
    0.83
    xual
    0.82
    anmar
    0.80
    ascus
    0.78
    umbn
    0.75
    anwhile
    0.72
    Activations Density 0.000%

    No Known Activations