© 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. 7-RES-JB
    11. 21222
    Prev
    Next
    INDEX
    Explanations

    terms related to specific roles or positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with services and roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.90
    ãĥķãĤ©
    -0.78
    Ext
    -0.74
    OX
    -0.69
     Tropical
    -0.67
     arrang
    -0.66
     mathemat
    -0.66
     Ext
    -0.65
    Measure
    -0.65
    ãĤ¦ãĤ¹
    -0.64
    POSITIVE LOGITS
    mans
    0.89
     persons
    0.88
     woman
    0.86
     person
    0.86
    tarians
    0.85
     cohort
    0.84
    lander
    0.84
     warriors
    0.83
     comrades
    0.83
     Females
    0.82
    Activations Density 0.565%

    No Known Activations