INDEX

Explanations

phrases that indicate uncertainty or reasons behind feelings and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 scénario

-0.47

hæng

-0.47

 leisure

-0.47

 hmot

-0.45

 Scenarios

-0.45

portál

-0.45

engarkan

-0.44

 Novel

-0.43

 scenarios

-0.43

度は

-0.42

POSITIVE LOGITS

Somehow

0.93

 Somehow

0.89

 strangely

0.85

исленность

0.82

protoimpl

0.78

SourceChecksum

0.78

 disambiguazione

0.78

 ModelExpression

0.76

 weirdly

0.75

 somehow

0.74

Activations Density 0.242%

phrases that indicate uncertainty or reasons behind feelings and actions

No Comments

No Known Activations