© 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. 9-RES-JB
    11. 16002
    Prev
    Next
    INDEX
    Explanations

    instances of possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "have" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshi
    -0.75
    TG
    -0.67
    etting
    -0.65
    >>\
    -0.64
    FIG
    -0.62
    ply
    -0.62
    inducing
    -0.59
    jam
    -0.59
    otally
    -0.59
    BT
    -0.57
    POSITIVE LOGITS
     recourse
    1.11
     plans
    0.97
     plenty
    0.91
     reservations
    0.89
     difficulty
    0.88
     trouble
    0.85
     doubts
    0.85
     visions
    0.84
     access
    0.84
     nightmares
    0.82
    Activations Density 0.155%

    No Known Activations