© 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. 4840
    Prev
    Next
    INDEX
    Explanations

    adjectives related to being strong or reliable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "solid" and its related terms

    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
    NetMessage
    -0.78
    llor
    -0.69
    xual
    -0.69
    Hop
    -0.68
     wisely
    -0.66
     stricken
    -0.64
     wrongly
    -0.63
    clipse
    -0.63
     dearly
    -0.62
    plugins
    -0.60
    POSITIVE LOGITS
    ified
    1.58
    ifying
    1.45
    arity
    1.28
    ifies
    1.28
    GoldMagikarp
    1.26
    ify
    1.24
    ification
    1.20
    ifier
    1.08
    ity
    1.07
    iary
    1.03
    Activations Density 0.051%

    No Known Activations