INDEX

Explanations

words related to users and customers

oai_token-act-pair · gpt-3.5-turbo

references to individuals or groups involved in various activities or contexts

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

YL

-0.72

achment

-0.67

LOD

-0.65

Enough

-0.64

sole

-0.63

OUT

-0.62

REDACTED

-0.62

eful

-0.61

;;;;;;;;;;;;

-0.58

ascar

-0.58

POSITIVE LOGITS

 beware

0.85

 forgot

0.80

aurus

0.78

 perceive

0.76

 weren

0.75

 visualize

0.75

are

0.74

hip

0.74

wana

0.73

 were

0.72

Activations Density 0.260%

words related to users and customers

references to individuals or groups involved in various activities or contexts

No Comments

No Known Activations