INDEX

Explanations

the prefix "sub-" followed by a word

oai_token-act-pair · gpt-3.5-turbo

the term "sub" followed by various numerical values

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

ILLE

-0.86

OHN

-0.83

 GOODMAN

-0.80

FORE

-0.78

 Zurich

-0.77

 Qiao

-0.77

 Lauder

-0.76

IELD

-0.73

 Muse

-0.72

ESCO

-0.71

POSITIVE LOGITS

missive

1.38

verting

1.24

mitter

1.21

sequent

1.19

mitted

1.15

sequently

1.15

mits

1.14

miss

1.12

missible

1.10

plot

1.09

Activations Density 0.015%

the prefix "sub-" followed by a word

the term "sub" followed by various numerical values

No Comments

No Known Activations