© 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. 20460
    Prev
    Next
    INDEX
    Explanations

    phrases related to absence of evidence or wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence of evidence or proof

    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
    anders
    -0.81
    aunts
    -0.78
    gypt
    -0.77
    amph
    -0.72
    sembly
    -0.72
    É
    -0.71
    byss
    -0.70
    often
    -0.70
     Streets
    -0.69
    chin
    -0.69
    POSITIVE LOGITS
     wrongdoing
    1.45
     malice
    1.32
     motive
    1.25
     basis
    1.25
     collusion
    1.24
     connection
    1.23
     culp
    1.22
     violation
    1.22
     nexus
    1.20
     rationale
    1.20
    Activations Density 0.209%

    No Known Activations