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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20375
    Prev
    Next
    INDEX
    Explanations

    phrases related to remains or remnants

    oai_token-act-pair · gpt-3.5-turbo

    references to remains or residues of people and things from various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IPS
    -0.77
    zai
    -0.77
    yout
    -0.71
    POR
    -0.71
    ussen
    -0.71
    wire
    -0.70
    idelines
    -0.70
    Wire
    -0.70
    SEE
    -0.70
    wcs
    -0.70
    POSITIVE LOGITS
     deceased
    1.05
     aborted
    0.96
     fallen
    0.91
     extinct
    0.90
     slain
    0.89
     defunct
    0.87
     burnt
    0.81
     antiquity
    0.80
     civilisation
    0.77
     remnants
    0.77
    Activations Density 0.220%

    No Known Activations