© 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. 6-RES-JB
    11. 9731
    Prev
    Next
    INDEX
    Explanations

    phrases related to utilizing resources or advantages for benefit

    oai_token-act-pair · gpt-3.5-turbo

    terms related to utilizing resources or maximizing potential

    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
    cas
    -1.02
     disbel
    -0.79
    mort
    -0.78
    ike
    -0.77
    ihad
    -0.75
     answ
    -0.71
    mos
    -0.71
    hemat
    -0.71
    nin
    -0.70
    ca
    -0.70
    POSITIVE LOGITS
     levers
    1.05
     leverage
    0.92
     strengths
    0.86
    ibility
    0.85
    IBLE
    0.83
    ibilities
    0.82
    Ability
    0.78
    ibly
    0.75
     resources
    0.75
     synergy
    0.74
    Activations Density 0.043%

    No Known Activations