INDEX

Explanations

newly released or surfaced information or products

oai_token-act-pair · gpt-3.5-turbo

terms related to the release or announcement of new products and information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

©¶æ

-0.85

alos

-0.83

athy

-0.74

adra

-0.74

Ĥİ

-0.72

sim

-0.71

atography

-0.70

rr

-0.70

hillary

-0.69

 teasp

-0.69

POSITIVE LOGITS

ynamic

0.68

 PowerPoint

0.68

 ones

0.65

 duck

0.64

 batch

0.62

 version

0.62

 fifth

0.62

 è£ıç

0.61

 secret

0.61

 versions

0.60

Activations Density 0.156%

newly released or surfaced information or products

terms related to the release or announcement of new products and information

No Comments

No Known Activations