INDEX

Explanations

titles or headings with strong emphasis or impact

oai_token-act-pair · gpt-3.5-turbo

frequent phrases and keywords related to questioning and recommendations

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

 superst

-0.71

 skilled

-0.68

omever

-0.67

 infl

-0.67

 crane

-0.66

 dred

-0.64

 appar

-0.64

 pressure

-0.64

 notor

-0.64

 masked

-0.64

POSITIVE LOGITS

 Affect

0.99

 Clause

0.98

Own

0.95

 Initiative

0.93

 Relationship

0.93

 Away

0.91

 Purpose

0.91

 Reviews

0.89

 Situation

0.89

 Content

0.89

Activations Density 0.455%

titles or headings with strong emphasis or impact

frequent phrases and keywords related to questioning and recommendations

No Comments

No Known Activations