INDEX

Explanations

the word "mysterious" with varying activation strengths for different occurrences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "mysterious" and its context

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

hers

-0.80

©¶æ

-0.80

enegger

-0.76

acus

-0.71

stein

-0.70

puter

-0.70

rien

-0.70

claimer

-0.69

fman

-0.69

ffen

-0.67

POSITIVE LOGITS

 occurrences

0.91

worldly

0.89

 mysterious

0.87

 suspic

0.83

 disappearance

0.82

 circumstances

0.78

 unexplained

0.77

 coincidence

0.77

 whispers

0.77

 anomal

0.75

Activations Density 0.023%

the word "mysterious" with varying activation strengths for different occurrences

occurrences of the word "mysterious" and its context

No Comments

No Known Activations