INDEX

Explanations

I'm sorry, but I couldn't find a clear pattern in the activations provided for neuron 4 to give a summary

oai_token-act-pair · gpt-3.5-turbo

references to "stuff" in a variety of contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emale

-0.77

vette

-0.69

bern

-0.69

deen

-0.68

stal

-0.68

HCR

-0.66

CVE

-0.65

INAL

-0.65

pent

-0.65

glas

-0.65

POSITIVE LOGITS

bags

1.01

 happening

0.90

 happens

0.87

hots

0.85

iness

0.83

 sack

0.79

bag

0.79

ious

0.78

 else

0.76

herer

0.75

Activations Density 0.031%

I'm sorry, but I couldn't find a clear pattern in the activations provided for neuron 4 to give a summary

references to "stuff" in a variety of contexts

No Comments

No Known Activations