© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13684
    Prev
    Next
    INDEX
    Explanations

    text related to discussions or decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    situations and decisions related to investigation or analysis

    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
     starve
    -0.72
     Kills
    -0.69
    Shut
    -0.68
     robbing
    -0.67
     persecut
    -0.65
    window
    -0.65
    evil
    -0.65
     Falling
    -0.65
     starving
    -0.63
     Dangerous
    -0.63
    POSITIVE LOGITS
     concluded
    1.23
     validated
    1.14
     finalized
    1.14
     agreed
    1.13
     summarized
    1.12
     unanimously
    1.09
     verified
    1.08
     submitted
    1.06
     complied
    1.06
     confirmed
    1.06
    Activations Density 0.385%

    No Known Activations