© 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. 6-RES-JB
    11. 13819
    Prev
    Next
    INDEX
    Explanations

    words related to conviction or being convinced

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "vin"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.92
    arers
    -0.73
    akening
    -0.69
    erity
    -0.67
    ngth
    -0.65
    awei
    -0.62
    adr
    -0.62
    HAEL
    -0.61
    bler
    -0.61
     Annotations
    -0.60
    POSITIVE LOGITS
    ces
    1.07
    eteen
    0.93
    cent
    0.92
    warm
    0.91
    eland
    0.89
    idia
    0.88
    eteenth
    0.86
    istic
    0.84
    ci
    0.84
    itus
    0.83
    Activations Density 0.032%

    No Known Activations