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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 9709
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of "dimension" or "dimensionality."

    oai_token-act-pair · gpt-3.5-turbo

    references to dimensions in various contexts

    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
    ony
    -0.80
    ublic
    -0.73
    roph
    -0.71
    ODUCT
    -0.68
    SY
    -0.67
    aque
    -0.66
    giving
    -0.66
    say
    -0.66
    -+
    -0.65
    rom
    -0.65
    POSITIVE LOGITS
     dimensions
    1.13
     dimension
    1.11
    dimension
    0.87
     Dimensions
    0.84
     dimensional
    0.83
    imensional
    0.81
     flares
    0.76
    ikuman
    0.75
    Factor
    0.75
     Dimension
    0.73
    Activations Density 0.005%

    No Known Activations