INDEX

Explanations

instances of the word "so"

oai_token-act-pair · gpt-3.5-turbo

the word "so" signaling a causal or consequential relationship

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 laun

-0.60

ICT

-0.58

Ranked

-0.57

ammy

-0.56

mast

-0.55

sha

-0.54

ropolitan

-0.54

intosh

-0.54

saf

-0.54

 breast

-0.53

POSITIVE LOGITS

oner

1.14

othe

1.12

bered

1.11

apy

0.98

othes

0.91

ooo

0.89

FTWARE

0.89

oths

0.86

aps

0.86

 congr

0.84

Activations Density 0.070%

instances of the word "so"

the word "so" signaling a causal or consequential relationship

No Comments

No Known Activations