INDEX

Explanations

terms related to specific names, likely related to a person or a place

oai_token-act-pair · gpt-3.5-turbo

words related to California geographic names and locations

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

bley

-0.75

 Cheong

-0.68

minecraft

-0.68

 Shutterstock

-0.67

\/\/

-0.64

 hypot

-0.60

ngth

-0.59

alter

-0.58

Fey

-0.57

ĸļ

-0.56

POSITIVE LOGITS

ornia

0.89

ASED

0.83

ãĤ¶

0.77

ãĥĥãĥī

0.75

phia

0.75

ĳå£«

0.72

ioxide

0.70

aneers

0.69

Ã§a

0.69

uration

0.68

Activations Density 0.083%

terms related to specific names, likely related to a person or a place

words related to California geographic names and locations

No Comments

No Known Activations