© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    sequences of letters that repeat multiple times in a row

    oai_token-act-pair · gpt-3.5-turbo

    elongated vowel sounds and repetitions

    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
     Prospect
    -0.82
     behavioural
    -0.71
     Mechdragon
    -0.71
     Redux
    -0.70
     compass
    -0.69
     lodging
    -0.69
     cooker
    -0.68
     seiz
    -0.67
     Compos
    -0.66
     Pers
    -0.66
    POSITIVE LOGITS
    ooo
    1.39
    oooo
    1.34
    aaaa
    1.25
    mmmm
    1.24
    oooooooo
    1.22
    mmm
    1.17
    OOOO
    1.16
    AAAA
    1.16
    !!!!!
    1.13
    oooooooooooooooo
    1.12
    Activations Density 0.089%

    No Known Activations