© 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. 4-RES-JB
    11. 14887
    Prev
    Next
    INDEX
    Explanations

    steps or sequences of instructions in a process

    oai_token-act-pair · gpt-3.5-turbo

    sequential actions or procedures

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

    No Comments

    Negative Logits
     Haram
    -0.69
    Ark
    -0.63
     Bie
    -0.62
    idad
    -0.62
    borgh
    -0.61
    cape
    -0.60
    caps
    -0.60
    hered
    -0.59
    pace
    -0.59
     Petersen
    -0.58
    POSITIVE LOGITS
    Ń·
    0.85
     proceeded
    0.81
    veland
    0.77
    ulhu
    0.75
     proceed
    0.74
    ————————————————
    0.72
    )</
    0.72
     Extras
    0.72
     =================================
    0.70
    raviolet
    0.70
    Activations Density 0.055%

    No Known Activations