INDEX

Explanations

phrases related to certainty or confirmation

oai_token-act-pair · gpt-3.5-turbo

strong expressions of denial or disagreement

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

icipated

-0.78

 Siber

-0.74

 bathrooms

-0.68

Tec

-0.67

 restrooms

-0.66

 Jensen

-0.64

 downstream

-0.61

 populated

-0.61

 transformer

-0.60

 exploits

-0.60

POSITIVE LOGITS

Yeah

1.11

Yes

1.01

Hmm

0.99

Answer

0.99

Exactly

0.98

YES

0.96

Correct

0.94

sir

0.93

Absolutely

0.92

 Exactly

0.91

Activations Density 0.533%

phrases related to certainty or confirmation

strong expressions of denial or disagreement

No Comments

No Known Activations