INDEX

Explanations

instances of the word "search" and related terms indicating information retrieval

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-1.05

testens

-0.84

httphttps

-0.82

LayoutPanel

-0.81

JNIEnv

-0.81

✨:

-0.81

Tikang

-0.80

@"/

-0.80

 createdBy

-0.80

fucker

-0.77

POSITIVE LOGITS

 SEARCH

1.68

 search

1.67

SEARCH

1.60

 Search

1.58

Search

1.51

search

1.43

 Searches

1.34

setSearch

1.34

 searched

1.31

 searches

1.30

Activations Density 0.034%

instances of the word "search" and related terms indicating information retrieval

No Comments

No Known Activations