INDEX

Explanations

proper nouns, particularly names of people

oai_token-act-pair · gpt-3.5-turbo

names and titles, particularly those with repetitive or unique letter patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĥ¼ãĥĨ

-0.77

FML

-0.72

BILITIES

-0.68

rency

-0.68

pmwiki

-0.67

ãĥĥãĥĪ

-0.63

 Collider

-0.61

erto

-0.58

SPONSORED

-0.58

fitting

-0.57

POSITIVE LOGITS

ovych

1.09

oslav

0.86

akov

0.74

ÅĤ

0.74

Yug

0.70

iku

0.66

 reckoning

0.63

doi

0.63

chev

0.62

bour

0.62

Activations Density 0.247%

proper nouns, particularly names of people

names and titles, particularly those with repetitive or unique letter patterns

No Comments

No Known Activations