INDEX

Explanations

salutations or references to the reader in a text

oai_token-act-pair · gpt-3.5-turbo

mentions of "Reader" in various forms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ering

-0.74

ela

-0.70

rament

-0.67

 Spears

-0.66

undy

-0.64

apes

-0.61

senal

-0.61

rait

-0.60

 Caldwell

-0.60

raltar

-0.60

POSITIVE LOGITS

 reader

0.89

 Reader

0.86

="#

0.81

OGR

0.80

 beware

0.76

sonian

0.75

boys

0.75

boy

0.74

 APPLIC

0.72

è£ħ

0.72

Activations Density 0.015%

salutations or references to the reader in a text

mentions of "Reader" in various forms

No Comments

No Known Activations