INDEX

Explanations

specific references to dates, names, and titles indicative of official or formal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 proces

-0.56

 Republicans

-0.54

 senti

-0.49

ạ

-0.49

 determin

-0.48

 contra

-0.47

umpulkan

-0.47

 Sustain

-0.47

 SEMI

-0.47

Semi

-0.46

POSITIVE LOGITS

thâu

0.98

+#+#

0.82

SharedDtor

0.81

PhysRev

0.79

writeFieldEnd

0.79

 EconPapers

0.78

parsedMessage

0.78

TintMode

0.78

Personendaten

0.77

sizeCache

0.76

Activations Density 0.211%

specific references to dates, names, and titles indicative of official or formal documentation

No Comments

No Known Activations