© 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. 9-RES-JB
    11. 2608
    Prev
    Next
    INDEX
    Explanations

    verbs in their past tense form with 'ed' or 'd'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corrections or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.73
    WAYS
    -0.72
    )=(
    -0.71
    ï¸
    -0.66
    tips
    -0.64
    tone
    -0.63
     Passion
    -0.62
     crates
    -0.62
    WAY
    -0.61
    ãĥĨãĤ£
    -0.61
    POSITIVE LOGITS
    ainer
    1.21
    rans
    1.20
    ribut
    1.16
    raction
    1.14
    raining
    1.12
    rench
    1.07
    reating
    1.04
    aking
    1.03
    itled
    1.03
    icent
    1.01
    Activations Density 0.015%

    No Known Activations