INDEX

Explanations

occurrences of the word "the" and phrases that denote specific locations or important places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 <=",

-0.49

ніципа

-0.49

)‏

-0.48

RTEE

-0.46

>({

-0.46

ровании

-0.46

 differenza

-0.46

 diferença

-0.44

Translatef

-0.44

 hindurch

-0.44

POSITIVE LOGITS

 nearest

0.99

 destination

0.99

 destinations

0.87

nearest

0.83

destination

0.79

 brink

0.78

 destina

0.77

findpost

0.74

 depths

0.73

AddTagHelper

0.73

Activations Density 0.278%

occurrences of the word "the" and phrases that denote specific locations or important places

No Comments

No Known Activations