INDEX

Explanations

words related to radio

oai_token-act-pair · gpt-3.5-turbo

references to radio

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rir

-0.84

laus

-0.77

 Snape

-0.75

jamin

-0.75

 Bane

-0.74

 Virtue

-0.73

rin

-0.72

-0.71

inho

-0.71

ortium

-0.70

POSITIVE LOGITS

activity

1.15

actively

1.14

active

1.07

 stations

1.00

 broadcasts

1.00

 station

0.91

 broadcasters

0.91

 antennas

0.91

 radio

0.89

 announcer

0.88

Activations Density 0.017%

words related to radio

references to radio

No Comments

No Known Activations