INDEX

Explanations

specific years or date ranges

oai_token-act-pair · gpt-3.5-turbo

dates and numerical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iants

-0.88

pora

-0.83

aminer

-0.81

iant

-0.79

arious

-0.72

ogical

-0.71

iance

-0.71

phia

-0.68

omorphic

-0.67

ical

-0.66

POSITIVE LOGITS

âĸĪâĸĪ

1.00

0.94

0.88

0.85

0.84

0.83

theless

0.82

0.81

Activations Density 0.011%

specific years or date ranges

dates and numerical references

No Comments

No Known Activations