INDEX

Explanations

terms related to basic concepts or foundational elements within text

oai_token-act-pair · gpt-3.5-turbo

the word "basically" and its repeated usage in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ey

-0.74

IDA

-0.71

acity

-0.71

yd

-0.68

rer

-0.67

yth

-0.66

imb

-0.65

lest

-0.64

icip

-0.64

yer

-0.64

POSITIVE LOGITS

 consisted

0.76

 basically

0.76

©¶æ¥µ

0.75

igslist

0.73

ength

0.72

 princ

0.71

 defin

0.70

 consists

0.70

 consist

0.70

rency

0.70

Activations Density 0.013%

terms related to basic concepts or foundational elements within text

the word "basically" and its repeated usage in different contexts

No Comments

No Known Activations