INDEX

Explanations

mentions of radio

oai_token-act-pair · gpt-3.5-turbo

mentions of radio

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rir

-0.90

-0.81

rg

-0.80

jamin

-0.78

AGES

-0.77

laus

-0.73

resses

-0.73

aws

-0.72

 Arbor

-0.70

================================================================

-0.70

POSITIVE LOGITS

 radio

1.17

 radios

1.08

 antennas

1.00

actively

0.98

 transmitter

0.95

 antenna

0.95

 announ

0.91

 stations

0.91

activity

0.91

radio

0.89

Activations Density 0.008%

mentions of radio

mentions of radio

No Comments

No Known Activations