© 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. 8-RES-JB
    11. 16793
    Prev
    Next
    INDEX
    Explanations

    references to the sun

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sun"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.98
    ussen
    -0.81
     captcha
    -0.73
     Hodg
    -0.67
    izabeth
    -0.66
    ij士
    -0.66
    kson
    -0.64
    ername
    -0.64
     posit
    -0.62
    leneck
    -0.62
    POSITIVE LOGITS
    shine
    1.17
    flower
    1.05
    burst
    1.05
    beam
    1.01
    sets
    1.01
    nah
    0.98
    light
    0.98
    spot
    0.96
    lit
    0.94
    ning
    0.93
    Activations Density 0.019%

    No Known Activations