INDEX

Explanations

words or phrases related to association or connection between different concepts or ideas

oai_token-act-pair · gpt-3.5-turbo

references to relational concepts and connections

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

 Slate

-0.73

fly

-0.69

airs

-0.69

ima

-0.69

utt

-0.67

ifter

-0.67

andel

-0.64

 Kaufman

-0.61

 Straw

-0.60

aan

-0.60

POSITIVE LOGITS

MpServer

1.02

ativity

0.86

phrine

0.78

 ancest

0.77

metry

0.75

ĸļ

0.73

 relate

0.73

worldly

0.72

 thereto

0.72

ability

0.72

Activations Density 0.028%

words or phrases related to association or connection between different concepts or ideas

references to relational concepts and connections

No Comments

No Known Activations