© 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. 2-RES-JB
    11. 12896
    Prev
    Next
    INDEX
    Explanations

    web links and document sources

    oai_token-act-pair · gpt-3.5-turbo

    references and citations in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istant
    -0.76
    Ñĭ
    -0.72
    ucket
    -0.72
    arks
    -0.69
    tered
    -0.68
    immer
    -0.66
     frogs
    -0.66
    dogs
    -0.66
     bats
    -0.66
    istically
    -0.65
    POSITIVE LOGITS
    Via
    1.19
     Via
    1.13
    clair
    1.08
    via
    0.88
    yss
    0.79
     Email
    0.76
    dayName
    0.75
    forward
    0.73
    aleb
    0.70
     via
    0.68
    Activations Density 0.009%

    No Known Activations