© 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. 11-RES-JB
    11. 4077
    Prev
    Next
    INDEX
    Explanations

    names or titles of people and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to responsibilities or actions associated with individuals, particularly in professional or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¯
    -0.69
    anus
    -0.64
    rahim
    -0.63
    cipled
    -0.60
    agos
    -0.60
    sov
    -0.59
    ivery
    -0.58
    rencies
    -0.57
    arius
    -0.56
    Magikarp
    -0.56
    POSITIVE LOGITS
     her
    2.64
     herself
    2.51
     she
    2.46
    She
    2.17
     hers
    2.16
    she
    2.14
     She
    1.99
    Her
    1.95
     SHE
    1.89
     Her
    1.72
    Activations Density 2.728%

    No Known Activations