© 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. 0-RES-JB
    11. 22475
    Prev
    Next
    INDEX
    Explanations

    proper nouns or abbreviations in all caps

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sana
    -0.79
     Ariel
    -0.75
     Jud
    -0.74
     Cind
    -0.74
     Osama
    -0.74
     Rend
    -0.74
     Ter
    -0.74
     Bashar
    -0.73
     Awoken
    -0.73
     Cond
    -0.72
    POSITIVE LOGITS
    RM
    2.55
    LR
    2.47
    BG
    2.35
    KR
    2.30
    LP
    2.28
    CN
    2.24
    LM
    2.22
    LT
    2.22
    NL
    2.21
    MG
    2.19
    Activations Density 0.040%

    No Known Activations