© 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. 1-RES-JB
    11. 16894
    Prev
    Next
    INDEX
    Explanations

    words related to heightened states or excessiveness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "hyper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ello
    -0.82
     Continued
    -0.74
    INGS
    -0.72
     Settlement
    -0.72
     Peoples
    -0.70
    ivity
    -0.70
    oured
    -0.69
    irements
    -0.69
    UE
    -0.69
    eca
    -0.69
    POSITIVE LOGITS
     hyper
    1.30
     hyp
    1.12
    bole
    1.11
    hyper
    1.09
    visor
    1.07
    bol
    1.00
    hyp
    0.92
    dimension
    0.88
     aggro
    0.83
     mascul
    0.82
    Activations Density 0.009%

    No Known Activations