INDEX

Explanations

years related to historical events

oai_token-act-pair · gpt-3.5-turbo

references to significant historical years and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

amin

-0.83

umen

-0.82

ende

-0.82

iant

-0.78

axis

-0.71

hus

-0.70

tan

-0.70

lig

-0.70

Marco

-0.70

attr

-0.69

POSITIVE LOGITS

1.11

1.09

ĸļ

1.04

1.00

0.94

0.90

0.89

Activations Density 0.012%

years related to historical events

references to significant historical years and events

No Comments

No Known Activations