© 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. 20246
    Prev
    Next
    INDEX
    Explanations

    instances where rules or violations are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or regulatory actions

    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
    uador
    -0.55
    DragonMagazine
    -0.54
    bably
    -0.53
    ©¶æ
    -0.52
    akespeare
    -0.49
     Architects
    -0.47
    ventus
    -0.47
    ĸļ
    -0.46
    icho
    -0.45
    ibaba
    -0.45
    POSITIVE LOGITS
    .?
    1.29
    .(
    1.23
    .
    1.23
    !.
    1.22
    .</
    1.19
    .'
    1.17
    .�
    1.16
     anymore
    1.14
    %.
    1.12
    .–
    1.12
    Activations Density 1.441%

    No Known Activations