© 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. 20240
    Prev
    Next
    INDEX
    Explanations

    phrases related to feedback or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or dissatisfaction

    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
    cedented
    -0.61
    imet
    -0.56
     unlawfully
    -0.56
    Enlarge
    -0.56
     unlawful
    -0.53
    ridor
    -0.53
    \":
    -0.53
    interstitial
    -0.52
     ultraviolet
    -0.51
     jointly
    -0.51
    POSITIVE LOGITS
     honestly
    0.97
     anyways
    0.90
    Anyway
    0.85
     however
    0.82
     admittedly
    0.81
     frankly
    0.78
     Anyway
    0.77
     anyway
    0.75
     tho
    0.74
     pity
    0.73
    Activations Density 1.008%

    No Known Activations