© 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. 21433
    Prev
    Next
    INDEX
    Explanations

    words related to mistreatment or mistakes

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "mistreatment" or "mistake."

    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
    phrine
    -0.71
    lishes
    -0.64
     Corpus
    -0.64
     scratch
    -0.62
    adesh
    -0.62
    study
    -0.58
     Jav
    -0.58
    mits
    -0.58
     Esc
    -0.56
    */(
    -0.56
    POSITIVE LOGITS
    reatment
    1.74
    reated
    1.63
    reating
    1.40
    rans
    1.30
    arget
    1.21
    ypes
    1.21
    aking
    1.18
    reat
    1.18
    resses
    1.13
    akable
    1.11
    Activations Density 0.020%

    No Known Activations