INDEX

Explanations

mentions of specific locations or entities as examples

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 besides

-0.81

leeve

-0.80

ea

-0.69

ontent

-0.67

 differs

-0.67

 solves

-0.66

 resembles

-0.66

EVA

-0.65

iliate

-0.65

stals

-0.65

POSITIVE LOGITS

 aforementioned

1.26

 slightest

1.01

 infamous

0.97

 entirety

0.91

 latter

0.87

 smallest

0.86

 likes

0.85

 shortest

0.83

 largest

0.83

 ones

0.83

Activations Density 0.184%

mentions of specific locations or entities as examples

occurrences of the word "the"

No Comments

No Known Activations