INDEX

Explanations

terms related to the city or concept of "York"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ork" in various contexts

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

ples

-0.77

 charity

-0.63

âĸ¬âĸ¬

-0.63

inav

-0.62

 Bethesda

-0.61

 tradem

-0.60

 vanilla

-0.60

ciples

-0.59

TRY

-0.59

ection

-0.58

POSITIVE LOGITS

ansas

1.23

ozy

1.01

crew

0.96

heimer

0.96

lift

0.94

atana

0.86

hire

0.86

owski

0.85

rait

0.84

asus

0.83

Activations Density 0.015%

terms related to the city or concept of "York"

occurrences of the substring "ork" in various contexts

No Comments

No Known Activations