INDEX

Explanations

conjunctions that indicate connections and comparisons in sentences

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

-0.57

-0.56

<eos>

-0.55

 information

-0.53

-0.52

two

-0.52

↵↵

-0.52

Ex

-0.51

POSITIVE LOGITS

存于互联网档案馆

0.89

 AssemblyCulture

0.87

ագրություններ

0.81

 Мексичка

0.81

tvguidetime

0.79

 незавершена

0.78

ształ

0.77

AnchorStyles

0.75

 виправивши

0.73

 كومونز

0.72

Activations Density 0.322%

conjunctions that indicate connections and comparisons in sentences

No Comments

No Known Activations