© 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. 10-RES-JB
    11. 12704
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating credibility and plausibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to plausibility and credibility

    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
    hops
    -0.97
    usterity
    -0.83
    sterdam
    -0.74
    paces
    -0.72
    horn
    -0.72
    ebus
    -0.69
     actionGroup
    -0.68
     Collector
    -0.68
    hirt
    -0.65
    cellence
    -0.65
    POSITIVE LOGITS
     hypotheses
    1.16
    evidence
    1.12
     evidence
    1.11
     allegation
    1.06
     proofs
    1.03
     explanations
    1.03
    iary
    1.02
     allegations
    1.01
     unbeliev
    1.01
     theories
    0.96
    Activations Density 0.133%

    No Known Activations