INDEX

Explanations

words with the substring 'ors'

oai_token-act-pair · gpt-3.5-turbo

the noun "ors," likely referencing a specific group or term relevant to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

SIM

-0.67

Wall

-0.66

Sus

-0.63

esville

-0.63

 msec

-0.62

DAY

-0.62

Fra

-0.61

LET

-0.61

ctors

-0.60

shell

-0.59

POSITIVE LOGITS

hips

1.37

hip

1.04

pace

1.03

poons

0.99

hift

0.97

pring

0.95

poon

0.89

mith

0.89

hin

0.86

orrow

0.86

Activations Density 0.016%

words with the substring 'ors'

the noun "ors," likely referencing a specific group or term relevant to various contexts

No Comments

No Known Activations