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. 10-RES-JB
    6. 15199
    Prev
    Next
    INDEX
    Explanations

    evidence or arguments supporting or refuting different ideas or claims

    oai_token-act-pair · gpt-3.5-turbo

    phrases that support or refute popular perceptions or notions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionGroup
    -0.79
    ufact
    -0.71
     Browse
    -0.71
     unfocusedRange
    -0.70
     GOODMAN
    -0.70
    Events
    -0.69
     overcame
    -0.68
    phabet
    -0.67
    ··
    -0.66
    meet
    -0.65
    POSITIVE LOGITS
     assertion
    1.69
     assertions
    1.66
     claim
    1.65
     notion
    1.61
     hypothesis
    1.60
     claims
    1.59
     hypotheses
    1.55
     assumption
    1.53
     allegation
    1.47
     theories
    1.47
    Activations Density 0.444%

    No Known Activations