INDEX

Explanations

mentions of and references to letters, alphabets, and typography

oai_token-act-pair · gpt-3.5-turbo

references to letters and the alphabet

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rolet

-0.85

oleon

-0.79

amera

-0.77

ESCO

-0.71

tics

-0.68

RELATED

-0.67

cdn

-0.66

Latest

-0.65

orsi

-0.65

ropolis

-0.64

POSITIVE LOGITS

 letters

1.03

letter

0.90

Letter

0.86

sworth

0.85

 letter

0.82

ymes

0.81

matically

0.79

acters

0.77

ames

0.76

 alphabet

0.75

Activations Density 0.018%

mentions of and references to letters, alphabets, and typography

references to letters and the alphabet

No Comments

No Known Activations