INDEX

Explanations

mentions of various forms of involvement or association

oai_token-act-pair · gpt-3.5-turbo

instances of the concept of "involvement" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Balanced

-0.73

imb

-0.72

sell

-0.71

eric

-0.67

©¶æ

-0.65

\\\\\\\\

-0.64

Float

-0.63

Jet

-0.63

 Panther

-0.62

 Tale

-0.61

POSITIVE LOGITS

enza

0.91

 involvement

0.90

ioned

0.84

annel

0.81

itaire

0.80

 involved

0.80

iveness

0.78

="#

0.76

iasco

0.75

 destro

0.74

Activations Density 0.010%

mentions of various forms of involvement or association

instances of the concept of "involvement" in various contexts

No Comments

No Known Activations