© 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. 11471
    Prev
    Next
    INDEX
    Explanations

    words related to communication and dialogue

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting symbols within text

    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
    ichick
    -0.85
    uggest
    -0.64
    racuse
    -0.62
    umably
    -0.62
    ibur
    -0.61
    ach
    -0.61
    onym
    -0.61
    hens
    -0.61
    odon
    -0.60
    oise
    -0.60
    POSITIVE LOGITS
    HEAD
    1.22
    HAM
    1.13
     PRES
    1.13
     PARK
    1.10
    WORK
    1.08
     EDITION
    1.07
    LET
    1.05
     NEWS
    1.05
     SCHOOL
    1.04
    MENT
    1.03
    Activations Density 0.362%

    No Known Activations