INDEX

Explanations

expressions related to issuing statements, warnings, rulings, and actions taken by authorities

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal actions and official statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aten

-0.81

artments

-0.76

ulhu

-0.72

apter

-0.70

utenberg

-0.68

Ã¨re

-0.68

natureconservancy

-0.66

hov

-0.65

onge

-0.65

ombies

-0.64

POSITIVE LOGITS

 apology

0.92

 condolences

0.84

 verdict

0.81

 decree

0.79

 Statement

0.75

 statement

0.74

 commencement

0.74

 memorandum

0.74

 licences

0.73

 interim

0.73

Activations Density 0.098%

expressions related to issuing statements, warnings, rulings, and actions taken by authorities

phrases related to legal actions and official statements

No Comments

No Known Activations