INDEX

Explanations

phrases related to closing, stopping, or shutting down something

oai_token-act-pair · gpt-3.5-turbo

phrases associated with being silenced or shut down

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ĸļ

-0.69

IVES

-0.66

ordan

-0.63

arya

-0.62

 abund

-0.62

ampton

-0.59

 Amit

-0.58

ãĥīãĥ©ãĤ´ãĥ³

-0.58

 covari

-0.57

ALLY

-0.57

POSITIVE LOGITS

tered

1.60

tering

1.43

downs

1.14

down

1.13

ters

1.07

 down

1.05

tle

1.05

offs

0.92

own

0.91

 downs

0.88

Activations Density 0.026%

phrases related to closing, stopping, or shutting down something

phrases associated with being silenced or shut down

No Comments

No Known Activations