© 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. 8-RES-JB
    11. 3046
    Prev
    Next
    INDEX
    Explanations

    phrases with possessive or belonging connotations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of apostrophes or contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stacks
    -0.68
     slic
    -0.65
     payday
    -0.64
     wallets
    -0.61
     sided
    -0.60
    ciating
    -0.60
    uilt
    -0.60
     Transfer
    -0.59
    tle
    -0.58
    uberty
    -0.58
    POSITIVE LOGITS
    oeuv
    0.97
    avez
    0.86
    Ag
    0.86
    Angelo
    0.85
    esp
    0.85
    Allah
    0.85
    Arc
    0.85
    hom
    0.84
    ét
    0.82
    Est
    0.82
    Activations Density 0.026%

    No Known Activations