INDEX

Explanations

names or words ending in 'ling'

oai_token-act-pair · gpt-3.5-turbo

forms of the word "ling."

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

ailable

-0.71

raviolet

-0.70

ĻĤ

-0.70

schild

-0.69

raints

-0.68

 Seym

-0.67

ORTS

-0.67

isites

-0.64

emis

-0.64

acco

-0.64

POSITIVE LOGITS

gren

1.00

gling

1.00

phrine

0.88

tons

0.87

ttes

0.84

ham

0.81

worth

0.80

berg

0.79

hammer

0.79

ishly

0.78

Activations Density 0.031%

names or words ending in 'ling'

forms of the word "ling."

No Comments

No Known Activations