© 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. 10-RES-JB
    11. 9971
    Prev
    Next
    INDEX
    Explanations

    phrases related to a current state or situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the current state or condition of something

    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
     Converted
    -0.61
    eness
    -0.59
    raved
    -0.57
     Advertisement
    -0.56
    izo
    -0.55
    ERY
    -0.54
    trak
    -0.54
    aple
    -0.53
    ño
    -0.53
    igmat
    -0.52
    POSITIVE LOGITS
    til
    0.74
    icably
    0.68
     moment
    0.68
    pite
    0.67
    ovember
    0.66
     regards
    0.65
    now
    0.65
     hence
    0.64
    behind
    0.64
     evidenced
    0.62
    Activations Density 0.199%

    No Known Activations