© 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. 7-RES-JB
    11. 8009
    Prev
    Next
    INDEX
    Explanations

    action-related words and numbers, especially related to steps or procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to steps in a process or sequential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.52
    etheless
    -0.42
     Canaver
    -0.37
    ãĥĺãĥ©
    -0.36
    ãĤ¼ãĤ¦ãĤ¹
    -0.36
    channelAvailability
    -0.36
    iannopoulos
    -0.36
    cedented
    -0.35
    unctions
    -0.35
    aterasu
    -0.34
    POSITIVE LOGITS
     CAD
    0.33
     droid
    0.33
     dyn
    0.32
     [âĢ¦]
    0.32
     [...]
    0.31
     dynam
    0.31
     elim
    0.31
     enlarg
    0.31
     choke
    0.29
     indu
    0.29
    Activations Density 4.507%

    No Known Activations