INDEX

Explanations

instances of the word "Got" at varying levels of strength

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "Got."

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

externalActionCode

-0.77

Ú

-0.68

advertisement

-0.67

ently

-0.67

uddin

-0.66

handedly

-0.64

FACE

-0.62

ARDS

-0.61

OUS

-0.60

ented

-0.60

POSITIVE LOGITS

cha

1.04

lass

0.87

glers

0.84

Got

0.80

nesday

0.76

luck

0.76

lahoma

0.75

terson

0.72

 Talent

0.72

zsche

0.70

Activations Density 0.028%

instances of the word "Got" at varying levels of strength

repeated instances of the word "Got."

No Comments

No Known Activations