© 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. 16515
    Prev
    Next
    INDEX
    Explanations

    instances where the word "here" is mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo
    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
    gency
    -0.59
    ains
    -0.58
    idine
    -0.55
     WATCHED
    -0.55
    selage
    -0.54
    arov
    -0.54
    jar
    -0.53
    locking
    -0.53
    ãĥ»
    -0.52
    awar
    -0.52
    POSITIVE LOGITS
     here
    3.27
     HERE
    2.36
     Here
    1.87
     herein
    1.72
    here
    1.69
    Here
    1.53
     hither
    1.33
     hereafter
    1.16
     below
    1.13
     tonight
    1.09
    Activations Density 0.052%

    No Known Activations