INDEX

Explanations

proper nouns related to specific locations or people

oai_token-act-pair · gpt-3.5-turbo

repeated references to "denver" and its variations

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

mercial

-0.86

è¦ļéĨĴ

-0.69

midt

-0.68

arella

-0.67

osate

-0.66

ebus

-0.66

ĪĴ

-0.65

Unix

-0.65

wcsstore

-0.64

odynamic

-0.64

POSITIVE LOGITS

ciating

0.79

ciation

0.74

hyde

0.72

sov

0.70

ãĤ¨ãĥ«

0.70

ance

0.68

ja

0.66

ukes

0.66

atis

0.64

issance

0.64

Activations Density 0.127%

proper nouns related to specific locations or people

repeated references to "denver" and its variations

No Comments

No Known Activations