© 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. 17311
    Prev
    Next
    INDEX
    Explanations

    details related to various events or incidents, including casualties, destruction, transportation details, and involvement of specific parties

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and classifications of various entities and situations

    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
    ãĤ¦ãĤ¹
    -0.88
    ãĤ¤ãĥĪ
    -0.74
    onom
    -0.74
    =>
    -0.70
    laughs
    -0.67
    âĶĢâĶĢâĶĢâĶĢ
    -0.67
    ocracy
    -0.66
     forgetting
    -0.64
     singular
    -0.64
    ãĥ¬
    -0.63
    POSITIVE LOGITS
     were
    1.21
     remained
    1.12
     appeared
    1.09
     accounted
    1.04
     flew
    1.03
     remain
    1.03
     soared
    1.02
     disappeared
    1.01
     arrived
    1.00
     declined
    1.00
    Activations Density 0.438%

    No Known Activations