INDEX

Explanations

phrases related to time

oai_token-act-pair · gpt-3.5-turbo

instances of the word "it" and its variations, indicating a focus on pronouns or references 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

scribe

-0.70

reference

-0.59

mission

-0.57

 partial

-0.57

 Highest

-0.57

abee

-0.56

 ILCS

-0.56

asure

-0.56

 remainder

-0.55

oided

-0.55

POSITIVE LOGITS

 seems

1.36

 appears

1.27

 turns

1.16

ain

1.15

 hasn

1.11

 rains

1.11

 looks

1.11

 transpired

1.05

unes

1.05

 Seems

1.05

Activations Density 0.215%

phrases related to time

instances of the word "it" and its variations, indicating a focus on pronouns or references in the text

No Comments

No Known Activations