© 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. 10-RES-JB
    11. 12227
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems and issues

    oai_token-act-pair · gpt-3.5-turbo

    statements about problems or challenges

    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
    haw
    -0.83
     congr
    -0.70
    riel
    -0.68
    ãĥ¼ãĥ³
    -0.68
    urch
    -0.67
     Pledge
    -0.66
    adel
    -0.66
     servings
    -0.65
     tours
    -0.65
    vision
    -0.63
    POSITIVE LOGITS
     exacerbated
    1.25
     compounded
    1.22
     solved
    1.21
     endemic
    1.03
     worsened
    0.96
     resolved
    0.94
     systemic
    0.93
     arising
    0.92
     inherent
    0.92
     unsolved
    0.92
    Activations Density 0.130%

    No Known Activations