INDEX

Explanations

references to specific geographical locations and historical groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-0.41

isielt

-0.41

uxxxx

-0.40

picasso

-0.37

 artísticas

-0.36

føl

-0.35

Kapcsolódó

-0.34

 graciosas

-0.34

 esfuer

-0.34

 históricas

-0.34

POSITIVE LOGITS

themselves

0.76

 themselves

0.74

their

0.60

Их

0.59

 loro

0.58

 Their

0.58

Their

0.58

 mereka

0.57

 Them

0.56

 InputDecoration

0.56

Activations Density 0.501%

references to specific geographical locations and historical groups

No Comments

No Known Activations