INDEX

Explanations

phrases related to adhering to instructions or guidelines

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize adherence or loyalty to rules, guidelines, or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flight

-0.66

APH

-0.65

 unfocusedRange

-0.64

EC

-0.64

terday

-0.64

jay

-0.63

VEL

-0.62

KEN

-0.61

AAF

-0.61

une

-0.60

POSITIVE LOGITS

handle

0.91

 plaster

0.91

river

0.81

rily

0.80

holder

0.76

lers

0.75

figure

0.74

handled

0.73

holders

0.73

 blender

0.72

Activations Density 0.032%

phrases related to adhering to instructions or guidelines

phrases that emphasize adherence or loyalty to rules, guidelines, or standards

No Comments

No Known Activations