© 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. 3-RES-JB
    11. 11328
    Prev
    Next
    INDEX
    Explanations

    Swedish or German words or characters

    oai_token-act-pair · gpt-3.5-turbo

    compound words or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.70
     corrid
    -0.61
     tremend
    -0.61
     GOODMAN
    -0.57
     suspic
    -0.57
    PDATE
    -0.56
     exha
    -0.56
     sudden
    -0.53
    ccording
    -0.52
    major
    -0.52
    POSITIVE LOGITS
    ensis
    0.85
     III
    0.64
    aten
    0.59
    dq
    0.58
    oglu
    0.58
    iev
    0.57
     ('
    0.57
    ombo
    0.57
    aii
    0.57
    uminium
    0.56
    Activations Density 0.982%

    No Known Activations