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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3890
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'freedom' or 'free' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "free" in various contexts

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

    No Comments

    Negative Logits
     Takeru
    -0.92
     sidx
    -0.82
    redients
    -0.72
     Stories
    -0.70
    amel
    -0.70
    ENTS
    -0.68
    iosyn
    -0.68
     therap
    -0.65
    emet
    -0.65
    iot
    -0.64
    POSITIVE LOGITS
    bies
    1.20
    bie
    1.07
     roam
    0.98
     downloadable
    0.82
    boot
    0.82
     federation
    0.77
     download
    0.75
    form
    0.75
     free
    0.74
     eBook
    0.73
    Activations Density 0.021%

    No Known Activations