© 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. 9744
    Prev
    Next
    INDEX
    Explanations

    references to specific movie titles or entities

    oai_token-act-pair · gpt-3.5-turbo

    titles or names of video games and their elements

    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
     glare
    -0.67
    aughed
    -0.67
     whipping
    -0.67
    ,,,,
    -0.60
    anwhile
    -0.59
    VIDIA
    -0.58
     ceremonial
    -0.58
    perature
    -0.58
     Glac
    -0.58
    ¶ħ
    -0.57
    POSITIVE LOGITS
    Wiki
    0.90
    ratom
    0.90
    Maker
    0.77
    Fest
    0.74
    soft
    0.72
     experien
    0.71
    RPG
    0.69
    TOR
    0.66
    Torrent
    0.65
    Nation
    0.65
    Activations Density 1.306%

    No Known Activations