INDEX

Explanations

terms related to search functionality and search engines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.84

 defaultstate

-0.80

Tikang

-0.78

LayoutPanel

-0.77

 postId

-0.75

*/].

-0.75

testens

-0.74

✨:

-0.74

iarkan

-0.74

 Duca

-0.74

POSITIVE LOGITS

 search

2.54

 SEARCH

2.38

 Search

2.35

SEARCH

2.29

Search

2.27

search

2.25

 searches

2.01

 searched

1.97

 Searches

1.93

setSearch

1.89

Activations Density 0.030%

terms related to search functionality and search engines

No Comments

No Known Activations