INDEX

Explanations

decimal numbers

oai_token-act-pair · gpt-3.5-turbo

numerical and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

SET

-0.77

 Ember

-0.73

 Chop

-0.72

Tun

-0.72

SCP

-0.72

 Mesa

-0.70

 Dover

-0.66

 Curiosity

-0.66

CAM

-0.65

 Apollo

-0.65

POSITIVE LOGITS

0.98

0.97

0.93

0.92

Activations Density 0.092%

decimal numbers

numerical and statistical data

No Comments

No Known Activations