INDEX

Explanations

settings-related terms and technical instructions

oai_token-act-pair · gpt-3.5-turbo

references to settings and options in a system or application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iterator

-0.79

å¥³

-0.78

ston

-0.78

ILY

-0.74

LI

-0.74

nesses

-0.74

past

-0.74

inosaur

-0.73

emic

-0.72

esome

-0.71

POSITIVE LOGITS

 settings

1.06

settings

0.86

 Settings

0.86

 Preferences

0.82

 knob

0.82

 tweaks

0.80

 menu

0.80

 presets

0.79

 Menu

0.79

 tweak

0.78

Activations Density 0.020%

settings-related terms and technical instructions

references to settings and options in a system or application

No Comments

No Known Activations