INDEX

Explanations

specific geographical locations or points of interest within a place

oai_token-act-pair · gpt-3.5-turbo

sentence endings and punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 volunte

-0.92

 bonded

-0.81

 entreprene

-0.81

 lockdown

-0.78

 escort

-0.76

 undercover

-0.76

 barric

-0.75

 haunted

-0.75

 waged

-0.75

 whistle

-0.74

POSITIVE LOGITS

 Therefore

1.74

 Thus

1.67

 Hence

1.59

 Consequently

1.53

 Interestingly

1.52

Therefore

1.51

 Conversely

1.50

Thus

1.45

 Assuming

1.45

 Similarly

1.44

Activations Density 0.388%

specific geographical locations or points of interest within a place

sentence endings and punctuation marks

No Comments

No Known Activations