© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 6292
    Prev
    Next
    INDEX
    Explanations

    references to movie review platform Rotten Tomatoes

    oai_token-act-pair · gpt-3.5-turbo

    references to the movie "Rotten Tomatoes" and related ratings or themes of decay and deterioration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oto
    -0.84
    trl
    -0.83
    ospons
    -0.82
    romy
    -0.82
    hover
    -0.73
    arro
    -0.72
    ajo
    -0.71
    abel
    -0.70
    ercise
    -0.70
    osponsors
    -0.70
    POSITIVE LOGITS
    otten
    0.98
     rotten
    0.92
     slate
    0.79
     bite
    0.74
     millenn
    0.73
     rotting
    0.72
     halls
    0.72
     Gleaming
    0.71
    atoes
    0.70
    Reviewed
    0.69
    Activations Density 0.015%

    No Known Activations