INDEX

Explanations

references to "snow" in various contexts

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

Tokens frequently preceding "hite", "den", or "cave"

np_acts-logits-general · gemini-2.0-flash

snow followed by specific words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 EconPapers

-0.99

 continúas

-0.82

 transfieras

-0.76

 AssemblyCulture

-0.72

Према

-0.62

Kanpo

-0.59

Vidite

-0.57

RegressionTest

-0.57

IMPORTED

-0.57

 beira

-0.55

POSITIVE LOGITS

 Snow

0.93

 snow

0.88

Snow

0.85

snow

0.85

 snowball

0.84

 SNOW

0.82

SNOW

0.75

 White

0.63

 white

0.60

 Snowflake

0.60

Activations Density 0.070%

references to "snow" in various contexts

Tokens frequently preceding "hite", "den", or "cave"

snow followed by specific words

No Comments

No Known Activations