INDEX

Explanations

law-related and procedural terms

oai_token-act-pair · gpt-3.5-turbo

specific titles, names, or references within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 americ

-0.69

 wedd

-0.62

íķ

-0.61

sid

-0.58

 Aust

-0.58

Arn

-0.57

 athlet

-0.57

ilk

-0.56

Charl

-0.55

 Kane

-0.55

POSITIVE LOGITS

issions

1.01

otation

0.77

odge

0.76

uctions

0.75

ules

0.74

vertisement

0.73

gment

0.72

gments

0.72

igsaw

0.72

pees

0.70

Activations Density 0.518%

law-related and procedural terms

specific titles, names, or references within a document

No Comments

No Known Activations