© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    phrases related to waking up or regaining consciousness after a change or event

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with psychological states and conditions

    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
     Cosponsors
    -0.88
    phalt
    -0.84
    Vote
    -0.80
    awei
    -0.77
     Infrastructure
    -0.77
    saf
    -0.77
    tackle
    -0.75
     BaseType
    -0.73
     Forge
    -0.71
     Forestry
    -0.71
    POSITIVE LOGITS
     hallucinations
    1.78
     trance
    1.64
     halluc
    1.64
     psychosis
    1.59
     insomnia
    1.56
     euph
    1.51
     depressive
    1.47
     epile
    1.44
     psychotic
    1.41
     flashbacks
    1.40
    Activations Density 0.623%

    No Known Activations