© 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. 1-RES-JB
    11. 24200
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of the word "free" in the context of services, trade, or rights

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "freedom" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Desert
    -0.76
     Mysteries
    -0.71
     Origin
    -0.71
     Humph
    -0.68
    emet
    -0.68
     Pavilion
    -0.66
     Takeru
    -0.66
    amel
    -0.66
    iot
    -0.65
     Held
    -0.65
    POSITIVE LOGITS
    bies
    1.23
     free
    0.96
    zers
    0.96
     roam
    0.95
    zing
    0.87
    bie
    0.83
     freedom
    0.82
     unrestricted
    0.82
    tarians
    0.82
     freedoms
    0.81
    Activations Density 0.031%

    No Known Activations