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

    Neuronpedia

    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. 7-RES-JB
    11. 9589
    Prev
    Next
    INDEX
    Explanations

    technical terms related to photography or cinematography

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uran
    -0.59
    Hug
    -0.56
    Stra
    -0.56
     Hawth
    -0.54
     Hob
    -0.54
     Entered
    -0.54
     Construct
    -0.54
     Dru
    -0.53
     Dawson
    -0.52
    Haw
    -0.52
    POSITIVE LOGITS
    utterstock
    0.59
     scares
    0.57
    ollah
    0.57
     Sabha
    0.54
    unct
    0.53
     [|
    0.53
    ebted
    0.52
    iley
    0.52
    Reviewer
    0.51
    ohm
    0.51
    Activations Density 0.384%

    No Known Activations