INDEX

Explanations

phrases related to movie titles or book titles

oai_token-act-pair · gpt-3.5-turbo

references to specific locations, notably in relation to known places or terms

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

 Bundes

-0.69

åĭ

-0.65

ħĭ

-0.65

ãĥĩ

-0.64

olutely

-0.62

ILA

-0.61

TEXTURE

-0.60

Ô

-0.59

ãĥīãĥ©ãĤ´ãĥ³

-0.59

 domin

-0.58

POSITIVE LOGITS

*/(

0.84

(<

0.74

igans

0.73

culus

0.72

breaks

0.70

oola

0.67

etheless

0.66

¬¼

0.64

Behind

0.62

else

0.61

Activations Density 0.128%

phrases related to movie titles or book titles

references to specific locations, notably in relation to known places or terms

No Comments

No Known Activations