© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    information related to personal attributes or descriptions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "who is" followed by a description or status of individuals

    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
    atche
    -0.79
    ivable
    -0.67
    phis
    -0.66
    efined
    -0.66
    ometers
    -0.65
    lations
    -0.65
    heastern
    -0.65
     Topics
    -0.64
    reat
    -0.64
    sers
    -0.64
    POSITIVE LOGITS
     overseeing
    0.86
     studying
    0.83
     stationed
    0.81
     married
    0.80
     unmarried
    0.79
     fluent
    0.79
     divorced
    0.79
     suing
    0.79
     autistic
    0.79
     divor
    0.78
    Activations Density 0.132%

    No Known Activations