© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20778
    Prev
    Next
    INDEX
    Explanations

    the pronoun "he" followed by an action or description

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific male individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Columb
    -0.59
    aj
    -0.59
    endment
    -0.59
     Joint
    -0.58
    ensable
    -0.58
     Bearing
    -0.57
    Bull
    -0.57
    anking
    -0.57
     Girls
    -0.56
    Temperature
    -0.56
    POSITIVE LOGITS
    'd
    1.05
    zbollah
    1.00
    eded
    1.00
    'll
    0.99
     encount
    0.82
     advoc
    0.81
     redes
    0.78
    resy
    0.75
    pherd
    0.75
    aps
    0.75
    Activations Density 0.233%

    No Known Activations