© 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. 3938
    Prev
    Next
    INDEX
    Explanations

    phrases with "co-" prefixes, such as co-owned, co-founded, co-ordinated

    oai_token-act-pair · gpt-3.5-turbo

    references to collaborative or joint efforts among individuals or groups

    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
     DRAG
    -0.72
     Panic
    -0.66
     Dickinson
    -0.65
     Simple
    -0.65
     AVG
    -0.65
     Compass
    -0.64
     Scrib
    -0.64
     Thin
    -0.63
     Belle
    -0.63
     Temper
    -0.63
    POSITIVE LOGITS
    signed
    1.07
    ordinate
    1.04
    interstitial
    1.04
    branded
    1.03
    authored
    1.03
    talk
    1.01
    cur
    1.01
    imposed
    1.00
    selected
    1.00
    ranking
    1.00
    Activations Density 0.048%

    No Known Activations