INDEX

Explanations

instances of the word "limited"

oai_token-act-pair · gpt-3.5-turbo

expressions related to restriction or limitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ranked

-0.85

bourne

-0.75

Mount

-0.72

ashington

-0.71

 Dirt

-0.69

went

-0.69

borne

-0.69

>>>>

-0.68

Old

-0.67

abad

-0.67

POSITIVE LOGITS

 limited

0.91

limited

0.89

 restricts

0.87

 exceptions

0.86

 liability

0.84

 collateral

0.83

 limitation

0.82

 limitations

0.81

 minded

0.81

 restriction

0.80

Activations Density 0.013%

instances of the word "limited"

expressions related to restriction or limitation

No Comments

No Known Activations