INDEX

Explanations

expressions of emotional responses and sentiments

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

ſelves

-0.78

glMatrixMode

-0.76

ſelf

-0.72

Efq

-0.71

 pleaſure

-0.69

 Schengen

-0.69

 Conſ

-0.68

 Viter

-0.67

 greateſt

-0.65

EOS

-0.65

POSITIVE LOGITS

 they

1.16

it

1.12

we

1.04

if

0.98

you

0.93

 there

0.90

he

0.88

 that

0.78

HasForeignKey

0.77

 someone

0.76

Activations Density 0.310%

expressions of emotional responses and sentiments

No Comments

No Known Activations