© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12754
    Prev
    Next
    INDEX
    Explanations

    mentions of mental health and well-being

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mental health and psychological status

    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
     Intent
    -0.72
    eer
    -0.66
     publication
    -0.65
     Commissioners
    -0.64
    ries
    -0.63
     Prospect
    -0.63
     Aval
    -0.62
     Cullen
    -0.62
     destinations
    -0.61
     Juliet
    -0.61
    POSITIVE LOGITS
    ependent
    0.86
     retarded
    0.85
    onding
    0.81
     defic
    0.80
    pecially
    0.78
    osure
    0.77
    @#&
    0.77
     challenged
    0.75
    otropic
    0.75
    rypt
    0.74
    Activations Density 0.010%

    No Known Activations