INDEX

Explanations

action-related verbs like "show", "demonstrate", and "demonstrated"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presentation of research findings or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

pour

-0.77

enty

-0.77

quer

-0.76

etting

-0.76

tesy

-0.75

inventoryQuantity

-0.73

nown

-0.70

taboola

-0.67

fell

-0.66

mire

-0.65

POSITIVE LOGITS

 convinc

1.16

how

1.15

why

0.93

 that

0.91

 unequivocally

0.88

 correlations

0.85

that

0.84

 whether

0.81

 empir

0.80

 parallels

0.79

Activations Density 0.232%

action-related verbs like "show", "demonstrate", and "demonstrated"

phrases indicating the presentation of research findings or evidence

No Comments

No Known Activations