© 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. 10-RES-JB
    11. 21469
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving or offering something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the act of providing or giving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     converge
    -0.65
     convergence
    -0.60
    etheless
    -0.59
     occurrences
    -0.59
     Cth
    -0.58
     occurrence
    -0.58
    Interstitial
    -0.58
    aten
    -0.57
    artifacts
    -0.57
    appa
    -0.56
    POSITIVE LOGITS
     opportunity
    0.96
     chance
    0.86
     permission
    0.83
    credit
    0.82
     allowance
    0.78
    freedom
    0.78
    license
    0.78
     latitude
    0.77
     choice
    0.77
     pointers
    0.77
    Activations Density 0.299%

    No Known Activations