INDEX

Explanations

names of doctors

oai_token-act-pair · gpt-3.5-turbo

references to various doctors and their names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

tumblr

-0.81

Ô

-0.79

rontal

-0.69

 sugg

-0.67

 voic

-0.67

 Sharing

-0.64

=]

-0.64

 stash

-0.63

 pocket

-0.62

ittees

-0.62

POSITIVE LOGITS

 Canaver

1.03

Bloom

0.82

aimon

0.71

 Carson

0.71

 Peck

0.71

 Chapman

0.70

 Fowler

0.69

 Barber

0.69

 Leigh

0.69

Sue

0.69

Activations Density 0.088%

names of doctors

references to various doctors and their names

No Comments

No Known Activations