© 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. 2-RES-JB
    11. 17816
    Prev
    Next
    INDEX
    Explanations

    references to a central location or focus point

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "center"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atson
    -0.72
    etimes
    -0.69
    areth
    -0.68
    BIT
    -0.67
    apons
    -0.67
    pload
    -0.66
     Griffith
    -0.64
    THER
    -0.64
    iggins
    -0.63
     cig
    -0.63
    POSITIVE LOGITS
    pieces
    1.13
    tenance
    0.88
    point
    0.86
     centers
    0.84
     fielder
    0.81
    uve
    0.81
     center
    0.80
    points
    0.75
    bard
    0.75
    vier
    0.74
    Activations Density 0.025%

    No Known Activations