© 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. 6867
    Prev
    Next
    INDEX
    Explanations

    conditional statements expressing potential future actions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating hypothetical situations

    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
    Dur
    -0.81
    FX
    -0.70
    quickShipAvailable
    -0.69
    Ps
    -0.66
     Balanced
    -0.66
    Pain
    -0.65
    IOR
    -0.64
     Detention
    -0.63
    COLOR
    -0.63
     Apart
    -0.63
    POSITIVE LOGITS
     succeed
    1.05
     recreate
    1.02
     quit
    1.00
    wered
    1.00
     be
    0.99
     give
    0.99
     come
    0.97
     become
    0.96
     take
    0.94
     survive
    0.94
    Activations Density 0.060%

    No Known Activations