© 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. 0-RES-JB
    11. 16364
    Prev
    Next
    INDEX
    Explanations

    nouns related to guidance or teaching

    oai_token-act-pair · gpt-3.5-turbo
    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
    Ô
    -0.90
    Æ
    -0.75
     Belg
    -0.75
    ignt
    -0.72
    BT
    -0.72
     recess
    -0.71
    Palest
    -0.69
     Tat
    -0.68
    bians
    -0.67
     Bett
    -0.67
    POSITIVE LOGITS
     mentor
    3.06
     mentors
    2.22
     guru
    2.09
     advisor
    1.98
     advisors
    1.65
     cohorts
    1.44
     collaborator
    1.35
     Guru
    1.34
     instructor
    1.34
     savior
    1.31
    Activations Density 0.056%

    No Known Activations