© 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. 3-RES-JB
    11. 8937
    Prev
    Next
    INDEX
    Explanations

    phrases related to established systems or processes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of established systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    incinn
    -0.81
    cest
    -0.81
    iscal
    -0.80
    gp
    -0.67
    onite
    -0.67
    rd
    -0.65
     spill
    -0.65
    vous
    -0.63
    agascar
    -0.63
    ights
    -0.63
    POSITIVE LOGITS
    bos
    0.93
    ername
    0.77
    holder
    0.76
     Places
    0.74
     stead
    0.72
    holders
    0.71
     Solitaire
    0.70
    WAYS
    0.70
     places
    0.69
     place
    0.67
    Activations Density 0.027%

    No Known Activations