© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    names or words related to a political or official context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "relief" and its variations

    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
    asket
    -0.85
     womb
    -0.67
    izable
    -0.67
    ities
    -0.67
    quished
    -0.66
    asonic
    -0.65
    antha
    -0.64
     Boone
    -0.64
    porting
    -0.64
    IFIED
    -0.64
    POSITIVE LOGITS
    doms
    1.39
    ornia
    1.15
    iciary
    0.90
    enance
    0.89
    lings
    0.87
    s
    0.85
    sf
    0.85
    uin
    0.84
    ief
    0.84
    ezvous
    0.79
    Activations Density 0.021%

    No Known Activations