© 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. 19705
    Prev
    Next
    INDEX
    Explanations

    words related to the periodic cycle of a day

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "di," often indicating discussions about various topics

    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
    ãģĨ
    -0.83
    éĹĺ
    -0.75
    DragonMagazine
    -0.74
     spare
    -0.74
     totality
    -0.73
    ãĤ¤ãĥĪ
    -0.73
    manship
    -0.70
     Seah
    -0.69
    INGS
    -0.68
    NetMessage
    -0.65
    POSITIVE LOGITS
    abol
    1.24
    ocese
    1.18
    agon
    1.17
    urnal
    1.14
    abolic
    1.13
    agram
    1.03
    utsch
    0.99
    agen
    0.95
    arist
    0.95
    acon
    0.94
    Activations Density 0.015%

    No Known Activations