© 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. 4-RES-JB
    11. 14883
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of warning, encouragement, or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conflict or confrontation

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

    No Comments

    Negative Logits
    çīĪ
    -0.71
    gamer
    -0.71
     Redemption
    -0.67
     Directors
    -0.66
     Alpha
    -0.64
     Factor
    -0.63
    WER
    -0.62
     Millions
    -0.62
     Mankind
    -0.61
     Enterprise
    -0.61
    POSITIVE LOGITS
    ishment
    1.81
    ished
    1.68
    ishing
    1.63
    ishers
    1.54
    isher
    1.52
    ishes
    1.47
    ishable
    1.30
    ition
    1.22
    itions
    1.21
    ish
    1.16
    Activations Density 0.031%

    No Known Activations