INDEX

Explanations

keywords related to beginners or novice users

oai_token-act-pair · gpt-3.5-turbo

terms related to beginners or novice individuals

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

ichick

-0.74

orter

-0.71

otions

-0.68

orie

-0.63

illo

-0.62

ame

-0.61

hetti

-0.61

ore

-0.60

 Hernandez

-0.60

away

-0.60

POSITIVE LOGITS

 Begin

1.02

 beginners

0.90

ners

0.87

 beginner

0.86

ctory

0.84

cest

0.78

 Defin

0.78

Course

0.74

 learners

0.73

Beg

0.73

Activations Density 0.050%

keywords related to beginners or novice users

terms related to beginners or novice individuals

No Comments

No Known Activations