© 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. 24017
    Prev
    Next
    INDEX
    Explanations

    ratings and reviews given to different entities or subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to favorability ratings or evaluations of performance

    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
    cel
    -0.78
     Alz
    -0.78
    working
    -0.75
    vas
    -0.72
    adr
    -0.72
    ansson
    -0.71
    bringing
    -0.69
    ships
    -0.69
    starter
    -0.69
    prus
    -0.69
    POSITIVE LOGITS
     rating
    1.52
     ratings
    1.40
     Ratings
    1.29
     Rating
    1.25
    Rating
    1.17
    rating
    0.97
     score
    0.94
     rated
    0.90
    âĺħâĺħ
    0.88
     scores
    0.87
    Activations Density 0.007%

    No Known Activations