INDEX

Explanations

phrases related to statements or declarations

oai_token-act-pair · gpt-3.5-turbo

phrases that reference declarations or statements made in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ipal

-0.74

 Flavoring

-0.71

 suscept

-0.69

 Carbuncle

-0.66

iffe

-0.65

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.63

 Torn

-0.63

ainted

-0.61

icago

-0.61

asi

-0.61

POSITIVE LOGITS

 unequivocally

0.87

 emphatically

0.78

rooms

0.71

 otherwise

0.71

 goodbye

0.71

 plainly

0.70

quo

0.68

reth

0.68

 boldly

0.68

 bluntly

0.68

Activations Density 0.032%

phrases related to statements or declarations

phrases that reference declarations or statements made in documents

No Comments

No Known Activations