INDEX

Explanations

pronouns 'me' or 'we' followed by an action or a statement

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "Let me" indicating a request for action or attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

NAS

-0.76

ELD

-0.70

ORED

-0.65

ILD

-0.65

senal

-0.64

inflamm

-0.60

bats

-0.60

 adolesc

-0.60

netflix

-0.59

 Seah

-0.58

POSITIVE LOGITS

 clarify

1.08

 assume

1.08

 assure

1.05

 reiterate

1.00

 emphasize

0.98

 conclude

0.97

 verify

0.96

 give

0.94

 introduce

0.94

 tell

0.92

Activations Density 0.039%

pronouns 'me' or 'we' followed by an action or a statement

instances of the phrase "Let me" indicating a request for action or attention

No Comments

No Known Activations