INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'a' 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lasses

-0.76

inances

-0.66

ARGET

-0.66

-0.65

Ö¼

-0.63

 pige

-0.62

 Adidas

-0.62

feat

-0.61

poons

-0.61

PLIED

-0.61

POSITIVE LOGITS

Ã±

1.18

BILITY

1.02

ption

0.99

Ã±a

0.97

veland

0.96

Ã°

0.96

emon

0.95

usterity

0.94

BILITIES

0.93

pling

0.93

Activations Density 0.096%

names of people

occurrences of the letter 'a' in various contexts

No Comments

No Known Activations