INDEX

Explanations

descriptions of physical features and attributes

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be" indicating states or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Income

-0.80

 Achieve

-0.73

 Universities

-0.71

 Criminal

-0.71

=-=-=-=-

-0.67

iversal

-0.66

 Opposition

-0.65

 attainment

-0.65

ivals

-0.65

 Individuals

-0.65

POSITIVE LOGITS

nt

0.88

 drying

0.86

 thicker

0.83

 supposed

0.80

 located

0.80

 scanned

0.76

 folded

0.76

 stocked

0.76

 healed

0.75

 worn

0.75

Activations Density 0.392%

descriptions of physical features and attributes

forms of the verb "to be" indicating states or conditions

No Comments

No Known Activations