© 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. 5555
    Prev
    Next
    INDEX
    Explanations

    cases of aggression or intense activity

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "guard" or "ward" related to protection or safeguarding

    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
    emb
    -0.91
    orig
    -0.70
    adra
    -0.59
    usb
    -0.59
     jour
    -0.58
    amen
    -0.58
    apore
    -0.58
     stumbling
    -0.58
    bi
    -0.57
     tripod
    -0.57
    POSITIVE LOGITS
    arding
    1.44
    arded
    1.35
    ards
    1.14
    ARDS
    0.98
    ertodd
    0.93
    ARD
    0.90
    ritic
    0.86
    ard
    0.84
    dinand
    0.80
    mallow
    0.79
    Activations Density 0.006%

    No Known Activations