© 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. 9-RES-JB
    11. 2601
    Prev
    Next
    INDEX
    Explanations

    items related to electronic devices and personal belongings

    oai_token-act-pair · gpt-3.5-turbo

    items associated with theft or illegal possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transitions
    -0.71
     gradual
    -0.67
    ularity
    -0.65
     attrition
    -0.64
     valleys
    -0.64
    requent
    -0.64
     experien
    -0.63
     adversity
    -0.63
    ationally
    -0.62
    inav
    -0.62
    POSITIVE LOGITS
     belonging
    1.35
     valued
    0.99
     confiscated
    0.97
     containing
    0.96
     stolen
    0.95
     totaling
    0.93
     seized
    0.92
     looted
    0.92
     stuffed
    0.92
     handwritten
    0.88
    Activations Density 0.394%

    No Known Activations