INDEX

Explanations

words related to interpretation and meaning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

$_"

-0.74

bibfield

-0.67

ovp

-0.65

agascar

-0.64

prelude

-0.64

Viited

-0.64

')")

-0.63

citenamefont

-0.63

BibitemShut

-0.62

ípios

-0.61

POSITIVE LOGITS

 Interpretation

0.74

 INTERPRET

0.68

 interpretation

0.67

 Interpret

0.66

 interpretations

0.65

 interpret

0.62

graphics

0.61

 interpr

0.57

 Interpreting

0.56

неопр

0.55

Activations Density 0.166%

words related to interpretation and meaning

No Comments

No Known Activations