© 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. 8-RES-JB
    11. 8929
    Prev
    Next
    INDEX
    Explanations

    words related to prototypes and testing

    oai_token-act-pair · gpt-3.5-turbo

    references to prototypes and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è£ħ
    -0.90
    manship
    -0.89
    forth
    -0.72
    edin
    -0.69
    LINE
    -0.67
     Tonight
    -0.66
    mable
    -0.64
     Sins
    -0.64
     visitor
    -0.63
    hyde
    -0.63
    POSITIVE LOGITS
    agonist
    1.44
    ected
    1.35
    ests
    1.31
    otyp
    1.28
    otypes
    1.26
    ocol
    1.24
    agonists
    1.21
    racted
    1.21
    ective
    1.20
    ection
    1.20
    Activations Density 0.050%

    No Known Activations