INDEX

Explanations

terms related to decay or decrease

oai_token-act-pair · gpt-3.5-turbo

words related to obfuscation or dilution of clarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

swick

-0.81

cade

-0.67

TERN

-0.61

 Labyrinth

-0.61

REL

-0.59

beit

-0.58

ANS

-0.57

rawled

-0.57

ortment

-0.56

Nev

-0.56

POSITIVE LOGITS

elight

0.75

hift

0.75

 havoc

0.75

imize

0.71

(-

0.70

 inconvenience

0.69

baugh

0.68

imal

0.67

atives

0.66

:(

0.66

Activations Density 0.132%

terms related to decay or decrease

words related to obfuscation or dilution of clarity

No Comments

No Known Activations