© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1776
    Prev
    Next
    INDEX
    Explanations

    statements related to strong or impactful actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of sentence endings or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidel
    -0.54
     signings
    -0.54
     acquisition
    -0.54
     mosqu
    -0.53
     disemb
    -0.52
     intruder
    -0.52
    !'"
    -0.51
    emic
    -0.51
     faint
    -0.51
     belly
    -0.51
    POSITIVE LOGITS
     Secondly
    1.16
     Âł
    1.03
    jpg
    1.02
     Therefore
    1.01
    ↵Âł
    1.01
     However
    1.01
     Additionally
    1.00
    tumblr
    0.99
     ³³
    0.99
     secondly
    0.98
    Activations Density 0.536%

    No Known Activations