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. 0-RES-JB
    6. 7487
    Prev
    Next
    INDEX
    Explanations

    phrases related to an organization or a specific company specifically through instances of the text that contain the word "Deltaprinter"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product or brand name

    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
     Carnage
    -0.63
     answering
    -0.63
     coy
    -0.60
     juggling
    -0.60
     surpass
    -0.59
     surgical
    -0.59
     maniac
    -0.59
     Companion
    -0.58
     snakes
    -0.58
     polio
    -0.58
    POSITIVE LOGITS
    elt
    4.59
    els
    1.60
    elf
    1.35
    eln
    1.31
    elta
    1.30
    elle
    1.26
    elled
    1.25
    ilt
    1.23
    ells
    1.20
    olt
    1.18
    Activations Density 0.012%

    No Known Activations