INDEX

Explanations

words related to specific actions or activities

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ulet

-0.59

QB

-0.58

bal

-0.58

trak

-0.57

zbollah

-0.56

respond

-0.55

 treating

-0.54

say

-0.54

Mub

-0.54

icle

-0.54

POSITIVE LOGITS

redients

1.22

tons

1.02

HAM

0.94

ame

0.72

icate

0.71

bats

0.71

quished

0.71

lass

0.70

GGGGGGGG

0.70

enance

0.69

Activations Density 0.132%

words related to specific actions or activities

gerunds and present participles used in various contexts

No Comments

No Known Activations