INDEX

Explanations

proper nouns related to famous personalities, places, or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ze" 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

 glim

-0.83

ials

-0.77

ially

-0.74

paced

-0.70

ainment

-0.69

istrate

-0.67

fman

-0.67

ancial

-0.66

cutting

-0.66

selling

-0.64

POSITIVE LOGITS

lda

1.32

ppelin

1.26

zinski

0.99

ppe

0.92

zza

0.90

itsch

0.88

uble

0.87

ppy

0.87

hov

0.86

eker

0.86

Activations Density 0.017%

proper nouns related to famous personalities, places, or entities

occurrences of the substring "ze" in various contexts

No Comments

No Known Activations