INDEX

Explanations

words related to historical eras or periods

oai_token-act-pair · gpt-3.5-turbo

references to specific historical periods or political administrations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rer

-0.83

swer

-0.83

 mathemat

-0.83

cards

-0.82

ers

-0.81

sie

-0.80

liga

-0.79

ortment

-0.79

olulu

-0.79

rament

-0.76

POSITIVE LOGITS

BILITY

0.80

Äĩ

0.73

ffiti

0.72

zza

0.68

Å

0.67

 reper

0.64

fters

0.64

orthy

0.63

Äį

0.63

jc

0.63

Activations Density 0.021%

words related to historical eras or periods

references to specific historical periods or political administrations

No Comments

No Known Activations