© 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. 2-RES-JB
    11. 9465
    Prev
    Next
    INDEX
    Explanations

    words related to getting rid of something or wiping it out completely

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the eradication of diseases, especially malaria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARE
    -0.90
    hift
    -0.76
    othal
    -0.75
     cave
    -0.66
    cair
    -0.66
    FACE
    -0.65
    terday
    -0.65
    fax
    -0.64
     calculus
    -0.64
     glances
    -0.64
    POSITIVE LOGITS
    icating
    1.28
    icated
    1.23
    ication
    1.19
    icator
    1.19
    icable
    1.08
    icators
    1.01
     erad
    0.98
    ications
    0.96
    iencies
    0.89
    itational
    0.88
    Activations Density 0.016%

    No Known Activations