© 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. 4779
    Prev
    Next
    INDEX
    Explanations

    the presence of titles or positions held by individuals

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "the" in various contexts

    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
    rums
    -0.79
     qualifies
    -0.73
    humans
    -0.72
     strengthens
    -0.71
    ageddon
    -0.71
    thood
    -0.68
    Characters
    -0.67
    RAFT
    -0.67
     VIDEOS
    -0.66
    mares
    -0.66
    POSITIVE LOGITS
     youngest
    1.30
     founder
    1.25
     chairman
    1.25
     oldest
    1.23
     director
    1.22
     eldest
    1.20
     deputy
    1.19
     chief
    1.19
     longest
    1.17
     president
    1.17
    Activations Density 0.110%

    No Known Activations