INDEX

Explanations

phrases related to television show airings and broadcasts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "air" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llan

-0.84

axter

-0.70

acqu

-0.69

ortium

-0.68

ophers

-0.65

ledge

-0.65

usalem

-0.64

nton

-0.64

Ã±a

-0.63

ansson

-0.62

POSITIVE LOGITS

ONY

0.95

waves

0.93

 airing

0.90

 Sundays

0.82

caster

0.81

 aired

0.81

NF

0.78

ONSORED

0.76

shows

0.76

 airs

0.76

Activations Density 0.039%

phrases related to television show airings and broadcasts

occurrences of the word "air" and its variations

No Comments

No Known Activations