INDEX

Explanations

numerical values within a specific structure or context

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly closing parentheses and brackets

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

ikuman

-0.79

iets

-0.78

loo

-0.73

eling

-0.72

ding

-0.72

 grip

-0.70

 catalog

-0.69

 tremend

-0.68

eled

-0.67

 suspic

-0.67

POSITIVE LOGITS

 Additionally

1.09

 Alternatively

1.02

 Therefore

1.01

 Furthermore

0.96

 Similarly

0.95

 Afterwards

0.94

 Likewise

0.92

 Consequently

0.91

 Interestingly

0.89

 Whilst

0.89

Activations Density 0.097%

numerical values within a specific structure or context

punctuation marks, particularly closing parentheses and brackets

No Comments

No Known Activations