© 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. 20369
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to the concept of "freeze" or halted action

    oai_token-act-pair · gpt-3.5-turbo

    terms related to freezing or cold conditions

    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
     Santos
    -0.73
     Vic
    -0.70
    td
    -0.68
    att
    -0.65
    udos
    -0.65
     Ort
    -0.64
     Nug
    -0.64
     Pag
    -0.63
    mus
    -0.63
    ns
    -0.62
    POSITIVE LOGITS
     freeze
    4.08
     freezes
    3.17
     Freeze
    2.54
     froze
    2.49
     freezing
    2.39
     frozen
    2.06
     freezer
    1.57
    rozen
    1.32
     moratorium
    1.23
     frost
    1.23
    Activations Density 0.010%

    No Known Activations