INDEX

Explanations

statements asserting or denying a specific belief or claim

oai_token-act-pair · gpt-3.5-turbo

statements of opinion or claims about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

udeau

-0.69

 mentions

-0.69

illon

-0.68

enture

-0.67

urry

-0.67

 note

-0.66

 Clarks

-0.66

onnaissance

-0.65

umbnails

-0.65

evin

-0.63

POSITIVE LOGITS

nt

1.25

 indeed

1.15

 somehow

1.06

 destined

1.03

not

1.01

 worth

0.99

 gonna

0.98

 going

0.98

 actually

0.97

 unlikely

0.93

Activations Density 0.356%

statements asserting or denying a specific belief or claim

statements of opinion or claims about various subjects

No Comments

No Known Activations