INDEX

Explanations

phrases related to understanding or comprehension

oai_token-act-pair · gpt-3.5-turbo

instances of the word "understand" and its variations

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

onies

-0.74

onto

-0.73

picking

-0.72

hire

-0.72

ONS

-0.66

boro

-0.65

inating

-0.65

rites

-0.64

Ranked

-0.64

powder

-0.64

POSITIVE LOGITS

why

1.27

WHY

1.19

how

1.10

why

0.97

 what

0.89

ably

0.86

 whats

0.82

HOW

0.75

 english

0.74

 nuances

0.73

Activations Density 0.067%

phrases related to understanding or comprehension

instances of the word "understand" and its variations

No Comments

No Known Activations