INDEX

Explanations

numerical values related to an increase or decrease

oai_token-act-pair · gpt-3.5-turbo

references to changes in statistics or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ancial

-0.91

leneck

-0.77

vic

-0.77

Limited

-0.74

igent

-0.73

acet

-0.73

grain

-0.72

sylv

-0.71

bered

-0.70

hai

-0.68

POSITIVE LOGITS

 whence

0.98

 afar

0.94

 baseline

0.92

 scratch

0.76

 previously

0.74

 heights

0.73

 previous

0.67

 thence

0.65

ibrary

0.63

 elsewhere

0.62

Activations Density 0.066%

numerical values related to an increase or decrease

references to changes in statistics or data points

No Comments

No Known Activations