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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13344
    Prev
    Next
    INDEX
    Explanations

    the word "counselor" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to counseling and counselors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     licences
    -0.73
     £
    -0.73
    £
    -0.71
     breeding
    -0.70
     Brut
    -0.69
     ¥
    -0.67
     revolutions
    -0.66
     organising
    -0.66
     âĤ¬
    -0.66
    âī
    -0.65
    POSITIVE LOGITS
     counselor
    3.75
     counselors
    2.60
     Counsel
    1.92
     coun
    1.84
     therapist
    1.75
     examiner
    1.36
     advisor
    1.28
     instructor
    1.23
     adviser
    1.21
     psychiatrist
    1.16
    Activations Density 0.038%

    No Known Activations