© 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. 0-RES-JB
    11. 20423
    Prev
    Next
    INDEX
    Explanations

    terms related to libertarianism, specifically the concept of freedom

    oai_token-act-pair · gpt-3.5-turbo

    references to freedom or related concepts

    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
     Inv
    -0.74
     tables
    -0.71
     Honor
    -0.68
     Avatar
    -0.67
     eyes
    -0.66
     Tables
    -0.65
     apart
    -0.62
     casts
    -0.62
     cast
    -0.61
     Var
    -0.61
    POSITIVE LOGITS
    fre
    4.27
    Fre
    2.45
     Freak
    1.64
     FRE
    1.39
     fre
    1.38
     freel
    1.09
    fan
    1.08
     Fre
    1.05
    slave
    1.05
    free
    1.02
    Activations Density 0.025%

    No Known Activations