INDEX

Explanations

conjunctions and phrases indicative of conditions or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

<bos>

-0.76

שְׁ

-0.66

brainly

-0.65

 faſt

-0.65

 Diony

-0.63

 setId

-0.62

 unauthorised

-0.61

∛

-0.61

 ſur

-0.61

aryen

-0.61

POSITIVE LOGITS

1.02

.,

0.83

but

0.83

 however

0.78

%,

0.78

(),

0.77

ViewFeatures

0.77

′,

0.77

,-,

0.77

*,

0.76

Activations Density 2.379%

conjunctions and phrases indicative of conditions or consequences

No Comments

No Known Activations