© 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. 7-RES-JB
    11. 17154
    Prev
    Next
    INDEX
    Explanations

    phrases related to considering or evaluating something

    oai_token-act-pair · gpt-3.5-turbo

    references to subjective assessments or judgments made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buses
    -0.63
    MAT
    -0.63
     airst
    -0.59
     arrows
    -0.59
     airplanes
    -0.58
    kered
    -0.58
     jets
    -0.57
    idon
    -0.56
    VIDIA
    -0.55
    --+
    -0.55
    POSITIVE LOGITS
     taboo
    0.80
    tical
    0.80
    soType
    0.70
    psc
    0.69
    é¾įå¥ij士
    0.68
     precedent
    0.68
    risk
    0.67
    ocide
    0.67
     nerv
    0.67
    ophile
    0.65
    Activations Density 0.157%

    No Known Activations