© 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. 8-RES-JB
    11. 16770
    Prev
    Next
    INDEX
    Explanations

    phrases denoting necessary conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exclusivity or limitations

    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
    ãĥĥãĥĪ
    -0.81
    auga
    -0.80
    ãĥ³
    -0.65
    omo
    -0.65
    ashington
    -0.64
    yssey
    -0.62
    activity
    -0.62
    lat
    -0.60
     Lat
    -0.60
    olon
    -0.59
    POSITIVE LOGITS
     insofar
    0.78
     spor
    0.74
    iffe
    0.74
     emergencies
    0.68
    hig
    0.67
    ifiable
    0.66
     authorised
    0.65
     ones
    0.64
     authenticated
    0.60
     fraction
    0.60
    Activations Density 0.371%

    No Known Activations