INDEX

Explanations

proper nouns, specifically names of individuals and locations

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

Str

-0.48

ResumeLayout

-0.47

Ch

-0.46

int

-0.45

nu

-0.45

 Today

-0.44

LayoutConstraint

-0.43

Pa

-0.43

POSITIVE LOGITS

 ſta

0.72

 Administrativna

0.70

 myſelf

0.69

 pleaſure

0.69

новниш

0.68

Rhestr

0.68

 bershka

0.68

 sandero

0.68

Життєпис

0.66

 crdi

0.66

Activations Density 0.162%

proper nouns, specifically names of individuals and locations

No Comments

No Known Activations

proper nouns, specifically names of individuals and locations

No Comments

No Known Activations