INDEX

Explanations

historical instances or examples that serve as a model or guide for future actions

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "precedent."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ongs

-0.75

ropolitan

-0.75

uster

-0.72

rug

-0.71

ulu

-0.70

uld

-0.67

aiman

-0.67

yan

-0.67

wer

-0.66

wagen

-0.66

POSITIVE LOGITS

 precedent

1.40

 precedence

1.16

DragonMagazine

1.15

 preced

1.12

chall

0.76

 playbook

0.70

ĸļ

0.69

 prev

0.69

 stacking

0.67

 rule

0.66

Activations Density 0.010%

historical instances or examples that serve as a model or guide for future actions

references to the concept of "precedent."

No Comments

No Known Activations