© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15154
    Prev
    Next
    INDEX
    Explanations

    advanced techniques or strategies used in various fields

    oai_token-act-pair · gpt-3.5-turbo

    mentions of methods and approaches in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OV
    -0.73
    athan
    -0.69
    rip
    -0.68
    plane
    -0.64
     Brotherhood
    -0.62
    OUS
    -0.61
    ded
    -0.61
    ghazi
    -0.60
    over
    -0.59
    oÄŁ
    -0.59
    POSITIVE LOGITS
    poons
    1.26
    ettings
    1.18
    afety
    1.14
    etter
    1.13
    mith
    1.12
    uggest
    1.10
    hops
    1.05
    cape
    1.01
    hooting
    1.00
    cale
    1.00
    Activations Density 0.095%

    No Known Activations