© 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. 10-RES-JB
    6. 8002
    Prev
    Next
    INDEX
    Explanations

    words related to hidden or unnoticed aspects

    oai_token-act-pair · gpt-3.5-turbo

    morphological variations of the prefix "und-" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.75
    Reviewer
    -0.69
     caut
    -0.67
     moth
    -0.66
    =-=-=-=-
    -0.66
     Aman
    -0.65
     runes
    -0.64
     Rivals
    -0.61
     constitu
    -0.59
    uala
    -0.59
    POSITIVE LOGITS
    ministic
    1.04
    rimination
    1.00
    lict
    0.96
    puted
    0.96
    urbed
    0.96
    ected
    0.93
    ressed
    0.93
    inguished
    0.92
    ended
    0.91
    inished
    0.91
    Activations Density 0.041%

    No Known Activations