INDEX

Explanations

sentences that indicate approval or consent in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 autorytatywna

-0.54

so

-0.53

 something

-0.52

 Something

-0.51

 simply

-0.51

Something

-0.51

@"/

-0.50

 qualcosa

-0.49

 quite

-0.48

hea

-0.47

POSITIVE LOGITS

CloseOperation

0.82

qrstuvwxyz

0.75

ſelves

0.75

aarrggbb

0.74

 صوتيه

0.68

ſelf

0.68

)');

0.68

NOPQRST

0.66

 themſelves

0.66

 Kessel

0.65

Activations Density 0.723%

sentences that indicate approval or consent in research contexts

No Comments

No Known Activations