© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7212
    Prev
    Next
    INDEX
    Explanations

    verbs related to various actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to personal experiences and decisions

    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
    ween
    -0.68
    sis
    -0.67
    geries
    -0.65
    wayne
    -0.63
     CLR
    -0.62
    idium
    -0.61
    Asia
    -0.60
    ¯¯¯¯
    -0.60
     Presidency
    -0.59
    bies
    -0.58
    POSITIVE LOGITS
     myself
    0.98
    EStream
    0.89
    poke
    0.79
    undai
    0.75
     sugg
    0.71
    yss
    0.71
     looph
    0.69
     reluct
    0.69
    é¾
    0.67
    ascript
    0.67
    Activations Density 0.422%

    No Known Activations