© 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. 4-RES-JB
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    phrases containing personal titles such as "Dr." along with names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or persona

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

    No Comments

    Negative Logits
    ulative
    -0.55
    ependent
    -0.55
    staking
    -0.54
    cipled
    -0.53
    utenberg
    -0.50
    ":[{"
    -0.50
    matical
    -0.49
     Kejriwal
    -0.49
    untled
    -0.49
     varied
    -0.48
    POSITIVE LOGITS
    .).
    0.67
    .''
    0.63
    ensis
    0.59
    *.
    0.58
    ".
    0.58
    '.
    0.57
    ''.
    0.55
    iani
    0.55
    .</
    0.55
    %.
    0.52
    Activations Density 2.507%

    No Known Activations