© 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. 6-RES-JB
    11. 2731
    Prev
    Next
    INDEX
    Explanations

    strong action verbs related to demonstration or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with structural or organizational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    knife
    -0.73
     nomine
    -0.68
    spin
    -0.64
    ppa
    -0.62
     kidneys
    -0.61
     revol
    -0.61
     Prin
    -0.61
     princ
    -0.61
     disob
    -0.60
     shoulders
    -0.59
    POSITIVE LOGITS
    ations
    1.38
    ments
    1.38
    ATIONS
    1.35
    ment
    1.35
    ATION
    1.34
    ation
    1.25
    ances
    1.18
    ATIONAL
    1.17
    ABLE
    1.16
    ably
    1.15
    Activations Density 0.141%

    No Known Activations