INDEX

Explanations

conclusive statements or transitions in arguments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

man

-0.74

ing

-0.70

hol

-0.64

’

-0.64

cap

-0.61

 τά

-0.61

dag

-0.61

cran

-0.59

Pil

-0.59

illa

-0.59

POSITIVE LOGITS

 therefore

1.91

Therefore

1.75

 Therefore

1.71

 therefor

1.65

therefore

1.58

 hence

1.35

 thus

1.33

 Portanto

1.30

Hence

1.28

 Hence

1.27

Activations Density 0.143%

conclusive statements or transitions in arguments

No Comments

No Known Activations