© 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. 20902
    Prev
    Next
    INDEX
    Explanations

    references to fans and enthusiasts of various topics and hobbies

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of fans or enthusiasts related to various interests or media

    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
     unmarked
    -0.65
    staff
    -0.60
    urated
    -0.59
     Pharma
    -0.58
    Reloaded
    -0.56
    tal
    -0.55
    judicial
    -0.54
    achable
    -0.54
     minions
    -0.54
    aceous
    -0.53
    POSITIVE LOGITS
     rejoice
    1.28
     beware
    0.97
     extraord
    0.94
    paces
    0.85
    hip
    0.84
    uckle
    0.83
     alike
    0.83
    adelphia
    0.81
     everywhere
    0.76
    atics
    0.74
    Activations Density 0.175%

    No Known Activations