© 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. 6-RES-JB
    11. 19809
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation marks, particularly periods

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REF
    -0.76
    »Ĵ
    -0.74
     awakening
    -0.66
    LOAD
    -0.66
     mosqu
    -0.64
    SW
    -0.64
     unemploy
    -0.58
    OAD
    -0.57
    onite
    -0.57
     wandered
    -0.56
    POSITIVE LOGITS
     SHARES
    0.82
     Shares
    0.76
     Emails
    0.72
    hran
    0.68
    20439
    0.65
    jpg
    0.64
     Thumbnails
    0.64
    apor
    0.64
     sidx
    0.63
    utive
    0.62
    Activations Density 0.036%

    No Known Activations