INDEX

Explanations

proper nouns followed by the suffix "-en"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the suffix "en"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Canaveral

-0.76

milo

-0.69

enhagen

-0.69

 hitch

-0.67

TPPStreamerBot

-0.65

 corrid

-0.65

 Seym

-0.65

 Nicarag

-0.65

ython

-0.62

 Ambro

-0.62

POSITIVE LOGITS

emies

1.17

berger

1.11

bach

1.10

wald

1.09

baum

1.06

heim

1.02

zyme

1.02

chant

0.99

ews

0.98

feld

0.97

Activations Density 0.052%

proper nouns followed by the suffix "-en"

occurrences of the suffix "en"

No Comments

No Known Activations