INDEX

Explanations

words with the prefix "b" followed by a single digit number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'b' in varying contexts

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

éĹĺ

-0.84

ãĤ¦ãĤ¹

-0.79

 Gutenberg

-0.76

OPLE

-0.74

IDENT

-0.74

ãĥ´ãĤ¡

-0.72

espie

-0.71

agate

-0.70

rolet

-0.70

Plex

-0.69

POSITIVE LOGITS

abb

1.00

rows

1.00

ibliography

0.99

ibli

0.97

uch

0.92

raid

0.87

hatt

0.87

idd

0.86

uffed

0.85

ulk

0.85

Activations Density 0.012%

words with the prefix "b" followed by a single digit number

occurrences of the letter 'b' in varying contexts

No Comments

No Known Activations