INDEX

Explanations

specific patterns of phrases that include the word "that"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that" indicating various clauses or phrases in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Returns

-0.72

laughs

-0.67

thumbnails

-0.62

NES

-0.58

REDACTED

-0.57

Installation

-0.57

aug

-0.56

Is

-0.55

Mech

-0.54

Beh

-0.54

POSITIVE LOGITS

are

1.37

 aren

1.35

 were

1.30

 weren

1.29

 involve

1.21

 comprise

1.18

 resemble

1.17

 circulate

1.16

 relate

1.16

 defy

1.15

Activations Density 0.199%

specific patterns of phrases that include the word "that"

instances of the word "that" indicating various clauses or phrases in the text

No Comments

No Known Activations