© 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. 4-RES-JB
    11. 10134
    Prev
    Next
    INDEX
    Explanations

    mentions of technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the technology industry

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

    No Comments

    Negative Logits
    lihood
    -0.92
    theless
    -0.87
     Grave
    -0.72
    staking
    -0.71
     Duty
    -0.71
     Parenthood
    -0.69
     Cly
    -0.68
     Wem
    -0.68
     Lakes
    -0.67
    ktop
    -0.67
    POSITIVE LOGITS
    Crunch
    1.08
     savvy
    1.07
     gadgets
    0.97
     gadget
    0.94
    sav
    0.91
    onomy
    0.88
    tech
    0.87
     tech
    0.85
     specs
    0.84
    irtual
    0.83
    Activations Density 0.014%

    No Known Activations