Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 46
    Prev
    Next
    INDEX
    Explanations

    strong verbs/actions and their outcomes/events

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or changes in state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    past tense verbs

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierre
    -0.55
    arij
    -0.53
    arsity
    -0.51
    idated
    -0.49
    $$$$
    -0.48
    izont
    -0.46
    ĪĴ
    -0.45
    emed
    -0.45
    odan
    -0.44
     equivalents
    -0.43
    POSITIVE LOGITS
    terness
    0.55
     largeDownload
    0.53
    NetMessage
    0.50
     showc
    0.49
    ĵĺ
    0.48
    ktop
    0.47
     Written
    0.46
    taboola
    0.45
    merce
    0.45
    othes
    0.44
    Activations Density 0.999%

    No Known Activations