© 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. 20115
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities or measurements related to volume

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "volume."

    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
    unes
    -0.74
    Construct
    -0.68
     Nether
    -0.66
    gotten
    -0.65
     Turing
    -0.64
     Paradox
    -0.63
    roads
    -0.63
    riad
    -0.61
     Express
    -0.61
    union
    -0.60
    POSITIVE LOGITS
     volumes
    1.28
     volume
    1.25
    Volume
    1.19
    volume
    1.17
     Volume
    1.03
    catentry
    0.92
    itatively
    0.87
    umes
    0.86
    omore
    0.84
     exha
    0.84
    Activations Density 0.007%

    No Known Activations