© 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. 21341
    Prev
    Next
    INDEX
    Explanations

    words related to challenges and difficulties

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to difficulties and complications

    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
    ologne
    -0.79
    olon
    -0.78
    ines
    -0.71
    frey
    -0.69
    ="#
    -0.68
    esse
    -0.68
    =#
    -0.68
    ounces
    -0.66
    onds
    -0.66
    hal
    -0.66
    POSITIVE LOGITS
     conflicting
    0.82
     wording
    0.76
     inconsistent
    0.76
     incomp
    0.76
     pacing
    0.74
     due
    0.74
    iquid
    0.74
     terminology
    0.74
     underest
    0.74
     assumptions
    0.73
    Activations Density 0.531%

    No Known Activations