INDEX

Explanations

references to entities, relationships, and comparisons in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

stdbool

-0.51

 same

-0.45

may

-0.44

#+#

-0.41

ässig

-0.40

↵↵

-0.40

одно

-0.40

is

-0.39

in

-0.39

Примітки

-0.39

POSITIVE LOGITS

setVerticalGroup

0.93

DockStyle

0.86

jsonwebtoken

0.80

ContentAsync

0.75

CodedInputStream

0.75

 BorderRadius

0.74

TemporalType

0.72

 تضيفلها

0.72

 AssemblyTitle

0.72

 gynhyrchwyd

0.71

Activations Density 0.375%

references to entities, relationships, and comparisons in a scientific context

No Comments

No Known Activations