Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22773
    Prev
    Next
    INDEX
    Explanations

    descriptions or evaluations of performance or progress

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports performance and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Cheong
    -0.62
     Polit
    -0.59
     testified
    -0.54
     law
    -0.52
     incidentally
    -0.52
     ACLU
    -0.52
     Doctors
    -0.52
     Investigative
    -0.51
    ibrary
    -0.51
    aughs
    -0.50
    POSITIVE LOGITS
     groove
    0.65
     teamwork
    0.65
     fanbase
    0.63
     optimum
    0.61
     fruition
    0.59
     cohesion
    0.59
     cohesive
    0.59
     parity
    0.58
     TEAM
    0.57
    dimension
    0.57
    Activations Density 1.125%

    No Known Activations