INDEX

Explanations

the pattern "ae" in words

oai_token-act-pair · gpt-3.5-turbo

various forms of the word "ae" and its occurrences in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ICK

-0.84

naire

-0.77

naires

-0.74

icked

-0.70

agers

-0.69

lich

-0.69

 Canadiens

-0.67

ENTION

-0.66

rified

-0.66

aged

-0.66

POSITIVE LOGITS

hler

1.11

gypt

1.02

lyn

1.01

lect

1.00

bsite

0.99

ldon

0.96

hner

0.94

zza

0.94

ger

0.93

lder

0.93

Activations Density 0.025%

the pattern "ae" in words

various forms of the word "ae" and its occurrences in context

No Comments

No Known Activations