© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1985
    Prev
    Next
    INDEX
    Explanations

    phrases related to determining or evaluating something

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "the" as a common structural element across different contexts

    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
    âĿ
    -0.69
    note
    -0.68
    frog
    -0.67
    tumblr
    -0.66
    Save
    -0.66
    hari
    -0.66
    NB
    -0.65
    OTS
    -0.65
    SPONSORED
    -0.63
    quished
    -0.63
    POSITIVE LOGITS
     extent
    1.59
     effectiveness
    1.37
     amount
    1.35
     likelihood
    1.34
     severity
    1.32
     outcome
    1.28
     adequ
    1.25
     direction
    1.25
     availability
    1.23
     efficacy
    1.21
    Activations Density 0.390%

    No Known Activations