© 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. 10225
    Prev
    Next
    INDEX
    Explanations

    details or elements that are closely related or associated with each other

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proximity or detailed attention

    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
    ICAN
    -0.79
     Chaser
    -0.71
     Mania
    -0.70
    ule
    -0.68
    ————————
    -0.64
     Bucket
    -0.63
     Jackets
    -0.63
     Mayhem
    -0.63
     Reasons
    -0.62
    ista
    -0.62
    POSITIVE LOGITS
     aligned
    0.96
     minded
    0.87
    wired
    0.85
     resembles
    0.83
     enough
    0.83
    minded
    0.82
     closely
    0.82
     connected
    0.81
     intertwined
    0.81
     tuned
    0.80
    Activations Density 0.010%

    No Known Activations