INDEX

Explanations

the token "kin" followed by a number, with higher activations for "kin10" as opposed to "kin9."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "kin" and its variations

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

 Seym

-0.77

ħĭ

-0.66

 Debian

-0.65

 unfocusedRange

-0.64

 Continued

-0.63

ISE

-0.63

CoC

-0.63

 reused

-0.61

 margin

-0.61

 Euph

-0.60

POSITIVE LOGITS

kin

1.18

etics

1.11

ners

1.07

etic

1.06

etically

1.01

osaurs

0.98

ning

0.97

nings

0.95

eman

0.90

ny

0.90

Activations Density 0.004%

the token "kin" followed by a number, with higher activations for "kin10" as opposed to "kin9."

instances of the word "kin" and its variations

No Comments

No Known Activations