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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22802
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of freedom, especially in the context of expression and speech

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of freedom, particularly in the context of speech and expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.76
    mers
    -0.71
     Dynasty
    -0.67
    itated
    -0.66
    ergy
    -0.65
    acan
    -0.65
    ded
    -0.63
    ENTS
    -0.63
    ents
    -0.63
    senal
    -0.63
    POSITIVE LOGITS
    bies
    1.00
     roam
    0.87
     guaranteed
    0.79
     Fighters
    0.79
     afforded
    0.76
     freedoms
    0.76
     unrestricted
    0.75
    Reviewer
    0.74
     captives
    0.74
    houses
    0.73
    Activations Density 0.034%

    No Known Activations