© 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. 9-RES-JB
    11. 17733
    Prev
    Next
    INDEX
    Explanations

    words related to psychological experiences or medical consequences

    oai_token-act-pair · gpt-3.5-turbo

    themes related to psychological and physical disturbances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.87
    Vote
    -0.81
     Cosponsors
    -0.79
    é¾
    -0.78
     BaseType
    -0.76
     Yard
    -0.75
    endor
    -0.75
     Equality
    -0.75
     Fisheries
    -0.75
    phalt
    -0.74
    POSITIVE LOGITS
     hallucinations
    1.72
     psychosis
    1.65
     insomnia
    1.65
     halluc
    1.56
     trance
    1.50
     relapse
    1.47
     depressive
    1.45
     epile
    1.44
     hypnot
    1.43
     psychotic
    1.43
    Activations Density 1.285%

    No Known Activations