INDEX

Explanations

concepts related to slopes and elevation changes

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

riwal

-0.65

hư

-0.56

ystis

-0.55

 للمعارف

-0.54

 Schilling

-0.53

JAKARTA

-0.53

WithFormat

-0.53

stall

-0.52

 vitreous

-0.52

ALIAN

-0.52

POSITIVE LOGITS

 steeper

1.02

 slopes

1.01

 slope

0.99

 steep

0.97

 sloping

0.96

 Slope

0.93

 hillside

0.92

slope

0.91

 hill

0.91

 hills

0.89

Activations Density 0.283%

concepts related to slopes and elevation changes

No Comments

No Known Activations