INDEX

Explanations

terms related to programming functions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 BufferedReader

-0.53

 rembour

-0.47

sprogramm

-0.47

 répar

-0.45

 bicchiere

-0.44

 asciug

-0.44

enumi

-0.43

 gambe

-0.43

kmal

-0.43

lück

-0.43

POSITIVE LOGITS

SourceChecksum

0.82

Jeografia

0.68

webElementXpaths

0.64

Билгалдахарш

0.63

 resourceCulture

0.62

 ligiloj

0.62

complexContent

0.61

논

0.60

 <<<<<<<<<<<<<<

0.59

Ārējās

0.59

Activations Density 0.060%

terms related to programming functions and parameters

No Comments

No Known Activations