© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6887
    Prev
    Next
    INDEX
    Explanations

    instances where someone is successful in achieving a goal or solving a problem

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capability or successful achievements

    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
     Parents
    -0.73
    rium
    -0.67
     Tradition
    -0.63
    email
    -0.62
     Nose
    -0.59
     laundry
    -0.57
     VIDEOS
    -0.56
    machine
    -0.56
     Flags
    -0.55
     Kendall
    -0.55
    POSITIVE LOGITS
    bodied
    1.02
    't
    0.84
    ioned
    0.84
    Reviewer
    0.77
    reys
    0.76
    istically
    0.75
     afford
    0.73
     bod
    0.71
     compe
    0.70
    untarily
    0.68
    Activations Density 0.040%

    No Known Activations