© 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. 9-RES-JB
    11. 18543
    Prev
    Next
    INDEX
    Explanations

    references to specific destinations or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to destinations and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osw
    -0.78
    interstitial
    -0.73
    flix
    -0.65
    esan
    -0.64
    Reviewer
    -0.63
    manship
    -0.62
    apy
    -0.62
    onson
    -0.60
    esome
    -0.60
    cular
    -0.57
    POSITIVE LOGITS
    roying
    1.33
    ruct
    1.31
    itute
    1.24
    ruction
    1.13
    inations
    1.11
    ination
    1.05
    itution
    1.02
    ined
    0.98
    iny
    0.92
    riot
    0.89
    Activations Density 0.058%

    No Known Activations