INDEX

Explanations

phrases that indicate personal experiences or perspectives, particularly concerning understanding and empathy

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

SupportActionBar

-0.55

 terecht

-0.54

 rechange

-0.54

tığı

-0.50

sì

-0.50

 brengen

-0.50

 faveur

-0.49

 BoxDecoration

-0.49

mybatisplus

-0.49

/**

-0.47

POSITIVE LOGITS

nessed

0.61

体会

0.61

 witness

0.61

Pranala

0.60

 CURIAM

0.58

 understand

0.57

 witnesses

0.56

expérience

0.54

 experience

0.54

 GetEnumerator

0.52

Activations Density 0.289%

phrases that indicate personal experiences or perspectives, particularly concerning understanding and empathy

No Comments

No Known Activations