© 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. 19854
    Prev
    Next
    INDEX
    Explanations

    words related to disappearance or missing objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to something or someone that is missing or has gone away

    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
     change
    -0.67
     disarm
    -0.67
     shift
    -0.66
     pay
    -0.66
     release
    -0.64
     shake
    -0.64
     exit
    -0.63
     move
    -0.63
     avail
    -0.62
     catch
    -0.61
    POSITIVE LOGITS
     disappeared
    2.03
     soared
    1.92
     surged
    1.90
     plummeted
    1.85
     climbed
    1.85
     crept
    1.82
     flourished
    1.81
     vanished
    1.80
     perished
    1.80
     died
    1.79
    Activations Density 0.058%

    No Known Activations