INDEX

Explanations

words related to visitors or guests

oai_token-act-pair · gpt-3.5-turbo

references to visitors or visitors' experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lain

-0.80

rum

-0.67

negie

-0.65

esson

-0.64

stood

-0.61

corn

-0.60

©¶æ

-0.60

 Cure

-0.58

SourceFile

-0.57

rade

-0.56

POSITIVE LOGITS

 attractions

0.91

hip

0.84

issance

0.80

cript

0.76

Reviewer

0.73

 visitors

0.73

 attraction

0.72

glers

0.71

 visiting

0.71

erv

0.71

Activations Density 0.034%

words related to visitors or guests

references to visitors or visitors' experiences

No Comments

No Known Activations