Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3873
    Prev
    Next
    INDEX
    Explanations

    words related to recovery, relief efforts, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of recovery in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    polit
    -0.70
     vetoed
    -0.68
     Seat
    -0.67
     caric
    -0.67
     Nath
    -0.66
    hon
    -0.65
     blasp
    -0.65
    omin
    -0.65
     Cth
    -0.64
     scrut
    -0.64
    POSITIVE LOGITS
     recovery
    4.00
     Recovery
    3.15
     recover
    2.45
    overy
    2.16
     recovering
    2.06
     recovered
    2.06
     recovers
    1.91
     Recover
    1.76
     rehabilitation
    1.70
     remission
    1.59
    Activations Density 0.020%

    No Known Activations