INDEX

Explanations

phrases related to evaluation or assessment

oai_token-act-pair · gpt-3.5-turbo

the term "overall" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Debor

-0.75

Caf

-0.74

 Frie

-0.69

Bry

-0.67

lez

-0.66

leon

-0.65

cells

-0.64

Mub

-0.64

chers

-0.64

 Ferry

-0.64

POSITIVE LOGITS

 stability

0.89

 momentum

0.87

 attractiveness

0.86

 usefulness

0.83

 improvement

0.79

 length

0.78

 effectiveness

0.78

 competitiveness

0.77

 satisfaction

0.77

 governance

0.77

Activations Density 0.032%

phrases related to evaluation or assessment

the term "overall" in various contexts

No Comments

No Known Activations