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. 7-RES-JB
    6. 16055
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or contrasts using the phrase "in many ways"

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate comparisons or evaluations of effectiveness or suitability

    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
     UCH
    -0.68
    EVA
    -0.68
     helicop
    -0.66
    wa
    -0.66
    CU
    -0.66
     grades
    -0.61
    ULAR
    -0.60
    idan
    -0.58
    alsa
    -0.58
     grade
    -0.57
    POSITIVE LOGITS
     resembles
    0.88
     resemble
    0.77
     analogous
    0.72
     stranger
    0.71
     parallels
    0.70
     resembled
    0.68
     Older
    0.67
    paralle
    0.67
     resembling
    0.65
    terday
    0.63
    Activations Density 0.049%

    No Known Activations