INDEX

Explanations

keywords related to additional information or actions

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Additional" and its variations in context, indicating an emphasis on supplementary information

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

ertodd

-0.77

aceae

-0.70

FORE

-0.70

bis

-0.69

cture

-0.69

same

-0.68

generic

-0.68

Lua

-0.68

Gra

-0.66

gemony

-0.65

POSITIVE LOGITS

judicial

1.07

 layers

1.01

 funds

0.93

 impetus

0.92

 manpower

0.92

 resources

0.88

 duties

0.88

 funding

0.85

 responsibilities

0.84

 information

0.84

Activations Density 0.041%

keywords related to additional information or actions

mentions of the word "Additional" and its variations in context, indicating an emphasis on supplementary information

No Comments

No Known Activations