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. 15133
    Prev
    Next
    INDEX
    Explanations

    facts or claims that are either supported or refuted by evidence or studies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating evidence or support regarding claims and hypotheses

    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
     actionGroup
    -1.06
    zie
    -0.95
    ktop
    -0.82
    ufact
    -0.72
    ophon
    -0.72
    ourning
    -0.70
    incinn
    -0.66
    artments
    -0.65
    enaries
    -0.64
    illes
    -0.64
    POSITIVE LOGITS
     assertions
    1.39
     assertion
    1.24
     debunked
    1.18
     falsehood
    1.16
     untrue
    1.14
     claims
    1.12
     hypotheses
    1.09
     factual
    1.08
     allegation
    1.07
     conjecture
    1.07
    Activations Density 1.117%

    No Known Activations