© 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. 115
    Prev
    Next
    INDEX
    Explanations

    verbs related to writing and communication

    oai_token-act-pair · gpt-3.5-turbo

    references to writing or content creation tasks

    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
     predators
    -0.73
    htar
    -0.69
    seekers
    -0.67
    omaly
    -0.64
     Persons
    -0.63
     sights
    -0.62
    eele
    -0.62
    Sensor
    -0.62
    HUD
    -0.61
    hai
    -0.60
    POSITIVE LOGITS
    bern
    0.77
    olkien
    0.74
    çļ
    0.70
    RW
    0.69
     aloud
    0.68
     journal
    0.68
    ophon
    0.66
    ilk
    0.65
    issance
    0.64
     journals
    0.64
    Activations Density 0.150%

    No Known Activations