INDEX

Explanations

the word "apparition" or variations of it

oai_token-act-pair · gpt-3.5-turbo

words related to recognition and approval in the context of applications and features

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

embed

-0.64

lift

-0.61

 tremend

-0.57

 upset

-0.56

utenberg

-0.56

push

-0.56

 Breitbart

-0.54

Rust

-0.54

LM

-0.53

Kit

-0.52

POSITIVE LOGITS

ciating

0.76

zona

0.76

utor

0.76

nces

0.75

illin

0.74

arios

0.73

ESE

0.71

 Nieto

0.70

heid

0.69

orneys

0.69

Activations Density 0.214%

the word "apparition" or variations of it

words related to recognition and approval in the context of applications and features

No Comments

No Known Activations