© 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. 2-RES-JB
    11. 8323
    Prev
    Next
    INDEX
    Explanations

    references to liberation or liberating actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    par
    -0.64
     Hale
    -0.60
    colo
    -0.59
     listing
    -0.59
    Sil
    -0.58
    xus
    -0.58
    KE
    -0.58
    WAYS
    -0.58
     Grimm
    -0.57
    enegger
    -0.57
    POSITIVE LOGITS
     liberated
    1.05
     liberate
    1.02
     liberating
    0.86
    raint
    0.83
     liberation
    0.81
    selves
    0.81
     emancipation
    0.80
    veland
    0.77
    nesday
    0.75
    piration
    0.74
    Activations Density 0.012%

    No Known Activations