INDEX

Explanations

proper nouns (particularly names) starting with 'Henry'

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Henry" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ramid

-0.97

ntil

-0.92

ãĥ£

-0.91

awaru

-0.88

cheon

-0.86

*/(

-0.86

alion

-0.82

eers

-0.81

atively

-0.80

umbai

-0.77

POSITIVE LOGITS

 Kissinger

1.11

 Rollins

1.10

 Ford

1.01

 VIII

1.01

Tud

0.94

Wad

0.85

 Miller

0.83

 Wink

0.80

shire

0.80

Ell

0.79

Activations Density 0.035%

proper nouns (particularly names) starting with 'Henry'

mentions of the name "Henry" in various contexts

No Comments

No Known Activations