© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20656
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    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
     guarding
    -0.61
    Äĩ
    -0.61
    eur
    -0.60
    mass
    -0.58
     melted
    -0.58
     creatively
    -0.58
    æ©
    -0.56
    onyms
    -0.54
    MAP
    -0.54
    00007
    -0.53
    POSITIVE LOGITS
    terday
    0.98
    theless
    0.90
    etheless
    0.88
    outheast
    0.84
    pace
    0.82
    omew
    0.82
    ales
    0.81
    ometime
    0.80
    iblings
    0.77
    ixty
    0.75
    Activations Density 0.126%

    No Known Activations