INDEX

Explanations

words related to computer system settings

oai_token-act-pair · gpt-3.5-turbo

references to configuration options or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ible

-0.80

INESS

-0.78

sylvania

-0.77

aughs

-0.75

iversary

-0.74

emic

-0.74

arding

-0.73

atform

-0.73

IVERS

-0.73

worthiness

-0.72

POSITIVE LOGITS

 settings

0.88

 menu

0.85

 tweak

0.78

 knob

0.78

 tweaks

0.78

 menus

0.77

 setting

0.77

 Menu

0.76

 sheet

0.74

 presets

0.74

Activations Density 0.035%

words related to computer system settings

references to configuration options or settings

No Comments

No Known Activations