INDEX

Explanations

phrases related to entering or participating in various actions or situations

oai_token-act-pair · gpt-3.5-turbo

multiple occurrences of the phrase "get in."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alike

-0.58

 faithfully

-0.57

 rall

-0.57

BIL

-0.57

 aptly

-0.56

=]

-0.56

ALD

-0.56

 abdom

-0.56

 ende

-0.55

 Marian

-0.55

POSITIVE LOGITS

ordinate

1.13

bred

1.05

offensive

1.01

itialized

1.00

jected

0.99

hibited

0.96

operative

0.95

animate

0.95

breeding

0.94

roads

0.94

Activations Density 0.079%

phrases related to entering or participating in various actions or situations

multiple occurrences of the phrase "get in."

No Comments

No Known Activations