INDEX

Explanations

words related to specific locations or place names

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'h'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Clicker

-0.77

enhagen

-0.72

aution

-0.71

 Collider

-0.70

eering

-0.67

 mosqu

-0.63

eers

-0.62

BALL

-0.60

 Weeks

-0.60

 conclud

-0.59

POSITIVE LOGITS

ulhu

1.24

agen

1.22

orses

1.21

ollow

1.13

ythm

1.13

onest

1.04

awk

1.02

ackers

1.01

ouston

1.00

ilde

1.00

Activations Density 0.058%

words related to specific locations or place names

instances of the letter 'h'

No Comments

No Known Activations