INDEX

Explanations

phrases related to policy and official documents

oai_token-act-pair · gpt-3.5-turbo

key terms associated with reports and recommendations

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

Laughs

-0.82

 anyways

-0.75

 bart

-0.73

ById

-0.72

lol

-0.71

 bartender

-0.69

erker

-0.68

!).

-0.67

;)

-0.67

?).

-0.66

POSITIVE LOGITS

 bilateral

0.78

 Fiscal

0.77

 Implementation

0.72

 humanitarian

0.72

ulner

0.69

 unacceptable

0.68

ilateral

0.67

 Government

0.66

 declass

0.66

 recommendations

0.65

Activations Density 0.882%

phrases related to policy and official documents

key terms associated with reports and recommendations

No Comments

No Known Activations