© 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. 4-RES-JB
    11. 9151
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific focus or attention on someone or something

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on" used in various contexts

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

    No Comments

    Negative Logits
    ptive
    -0.78
    MODE
    -0.77
    ptives
    -0.77
    SourceFile
    -0.76
    BIP
    -0.71
    amus
    -0.71
    INESS
    -0.71
    DragonMagazine
    -0.69
    Types
    -0.68
    URA
    -0.68
    POSITIVE LOGITS
     behalf
    1.44
    coming
    1.19
    etime
    1.13
    erous
    1.05
    eness
    1.04
     occasion
    1.00
    eday
    0.99
    shore
    0.95
    sets
    0.95
    site
    0.93
    Activations Density 0.348%

    No Known Activations