© 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. 15177
    Prev
    Next
    INDEX
    Explanations

    statements or quotes attributed to someone, especially in regard to their actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    statements made by various companies or individuals regarding their actions or opinions

    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
    ãĥ¡
    -0.74
    cffffcc
    -0.73
    Occup
    -0.71
    trump
    -0.70
    à¦
    -0.66
    atown
    -0.65
    gone
    -0.64
    alias
    -0.64
    env
    -0.64
    ãĥ´
    -0.63
    POSITIVE LOGITS
     yesterday
    0.80
     its
    0.79
     goodbye
    0.75
     earlier
    0.70
     warranties
    0.69
     they
    0.66
    urances
    0.66
     DSM
    0.65
     troopers
    0.65
     partnerships
    0.64
    Activations Density 0.185%

    No Known Activations