© 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. 7-RES-JB
    11. 8005
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to tournament structures

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive match formats or rankings

    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
    ĸļ
    -0.81
    ²¾
    -0.66
    hyde
    -0.64
    FINE
    -0.63
    iko
    -0.60
     veins
    -0.59
    pora
    -0.59
    ADD
    -0.59
    hole
    -0.59
    earchers
    -0.58
    POSITIVE LOGITS
     outcomes
    0.72
     behaved
    0.71
     Worst
    0.70
     luck
    0.69
     scenario
    0.67
    lihood
    0.64
     outcome
    0.61
     odds
    0.60
    owship
    0.60
     lawy
    0.59
    Activations Density 0.135%

    No Known Activations