INDEX

Explanations

phrases related to feeling comfortable or uncomfortable in various situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "comfortable" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

arcity

-0.80

vernment

-0.70

*/(

-0.69

iseum

-0.68

bard

-0.67

acio

-0.66

ggles

-0.65

ongyang

-0.65

izons

-0.63

bey

-0.63

POSITIVE LOGITS

 enough

1.07

 knowing

0.94

 discussing

0.93

 commenting

0.91

 interacting

0.89

 doing

0.89

 disclosing

0.88

 wearing

0.87

 expressing

0.87

 performing

0.86

Activations Density 0.049%

phrases related to feeling comfortable or uncomfortable in various situations

instances of the word "comfortable" and its variations

No Comments

No Known Activations