INDEX

Explanations

specific technical terms and identifiers related to programming and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 utafitiHapana

-0.66

 resourceCulture

-0.49

AutoScaleMode

-0.47

ably

-0.44

ayant

-0.43

keta

-0.41

 насељу

-0.41

.(*

-0.41

 Wayback

-0.40

teten

-0.40

POSITIVE LOGITS

InputTagHelper

0.69

 itſelf

0.65

ItemBackground

0.65

rąg

0.64

DockStyle

0.60

imarães

0.60

 CURLOPT

0.59

GRANTED

0.58

mingbird

0.58

合衆

0.57

Activations Density 0.173%

specific technical terms and identifiers related to programming and data handling

No Comments

No Known Activations