© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12696
    Prev
    Next
    INDEX
    Explanations

    technical and functional features described in a context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or enabling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bloomberg
    -0.80
    fig
    -0.80
    Brexit
    -0.72
    ax
    -0.68
    Rex
    -0.66
    Asia
    -0.65
    deals
    -0.65
    ageddon
    -0.65
    AIDS
    -0.63
    leground
    -0.63
    POSITIVE LOGITS
     wearer
    1.64
     slightest
    1.42
     recipient
    1.40
     purchaser
    1.33
     user
    1.33
     attacker
    1.32
     sender
    1.30
     participant
    1.27
     viewer
    1.26
     practitioner
    1.25
    Activations Density 0.413%

    No Known Activations