INDEX

Explanations

numbers or position-related words

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" and its variants in various contexts

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

âĢİ

-0.81

Links

-0.77

letters

-0.76

forth

-0.72

reports

-0.72

evidence

-0.71

FontSize

-0.71

Sources

-0.71

Reports

-0.69

Contents

-0.66

POSITIVE LOGITS

rouse

1.10

 bunch

1.06

lot

1.02

 person

1.01

uras

1.00

 particular

0.97

 multitude

0.88

 dime

0.87

 stranger

0.87

 single

0.86

Activations Density 0.681%

numbers or position-related words

the indefinite article "a" and its variants in various contexts

No Comments

No Known Activations