INDEX

Explanations

technical terms related to various settings and configurations

oai_token-act-pair · gpt-3.5-turbo

references to settings and configurations in various contexts

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

nesses

-0.80

emic

-0.79

osaurs

-0.76

INESS

-0.75

Hai

-0.73

enary

-0.73

å¥³

-0.72

 Chaser

-0.72

ston

-0.72

LI

-0.72

POSITIVE LOGITS

 settings

1.06

 knob

0.93

settings

0.90

 menu

0.90

 presets

0.84

 tweaks

0.84

 toolbar

0.83

 Settings

0.82

 tweak

0.82

 drawer

0.81

Activations Density 0.034%

technical terms related to various settings and configurations

references to settings and configurations in various contexts

No Comments

No Known Activations