© 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. 3-RES-JB
    11. 22018
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles indicating ongoing actions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    so
    -0.64
     assumes
    -0.61
     subsequent
    -0.61
    sac
    -0.61
     grouping
    -0.60
    Discussion
    -0.58
    lo
    -0.58
    cation
    -0.58
    Tim
    -0.57
    dos
    -0.57
    POSITIVE LOGITS
    urated
    0.86
    redients
    0.74
     Canaver
    0.73
    ivable
    0.68
    ADRA
    0.66
    ependent
    0.66
    allery
    0.66
    utical
    0.66
    itored
    0.66
     suspic
    0.66
    Activations Density 0.400%

    No Known Activations