© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23875
    Prev
    Next
    INDEX
    Explanations

    ratings on a numerical scale, such as movie ratings

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.97
     Gor
    -0.84
     Briggs
    -0.73
     Bord
    -0.71
     Bos
    -0.70
    bones
    -0.69
     Mn
    -0.69
     Rutherford
    -0.67
    onite
    -0.66
     gobl
    -0.65
    POSITIVE LOGITS
    00
    2.27
    01
    1.45
    0010
    1.43
    0100
    1.40
     00
    1.39
    008
    1.33
    005
    1.28
    02
    1.28
    003
    1.27
    00200000
    1.25
    Activations Density 0.054%

    No Known Activations