INDEX

Explanations

phrases related to specific names or locations

oai_token-act-pair · gpt-3.5-turbo

references to specific entities or characters, particularly in the context of names and titles

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

 partName

-0.76

//[

-0.75

ãĥĩãĤ£

-0.75

Ingredients

-0.68

 Apprentice

-0.67

ãĥĵ

-0.67

VIEW

-0.66

ãĥĢ

-0.66

FIELD

-0.66

ãĥīãĥ©ãĤ´ãĥ³

-0.65

POSITIVE LOGITS

ulum

1.05

ules

0.93

atility

0.93

uble

0.85

ulate

0.84

ulated

0.84

ulates

0.81

pty

0.80

ulo

0.80

tc

0.79

Activations Density 0.050%

phrases related to specific names or locations

references to specific entities or characters, particularly in the context of names and titles

No Comments

No Known Activations