INDEX

Explanations

dates written in a specific format: month, day, and year separated by commas

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically commas

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

 corridors

-0.64

 boosters

-0.61

 secretaries

-0.58

 conferences

-0.54

 carriers

-0.54

 flares

-0.53

 predec

-0.53

 briefs

-0.53

 seam

-0.53

 cartridges

-0.52

POSITIVE LOGITS

1.25

1.15

1.14

1.09

1.06

0.99

0.96

0.94

0.92

Activations Density 0.037%

dates written in a specific format: month, day, and year separated by commas

punctuation marks, specifically commas

No Comments

No Known Activations