INDEX

Explanations

names or terms with the prefix "b" followed by a high relevance value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'b'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lauder

-0.64

DEM

-0.60

 Gutenberg

-0.60

bilt

-0.60

 Idlib

-0.59

enium

-0.59

 Lear

-0.58

 Porsche

-0.58

 Pharaoh

-0.57

Magikarp

-0.57

POSITIVE LOGITS

rief

1.34

odies

1.25

ruary

1.15

amboo

1.12

attery

1.10

reath

1.10

ibli

1.09

rities

1.09

rows

1.07

ulk

1.07

Activations Density 0.076%

names or terms with the prefix "b" followed by a high relevance value

occurrences of the letter 'b'

No Comments

No Known Activations

names or terms with the prefix "b" followed by a high relevance value

occurrences of the letter 'b'

No Comments

No Known Activations