INDEX

Explanations

the word "seemingly" appearing in the text

oai_token-act-pair · gpt-3.5-turbo

the word "seemingly" and expressions indicating a perception versus reality distinction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rike

-0.76

rikes

-0.73

imeter

-0.70

orters

-0.68

"}],"

-0.67

ppers

-0.67

llers

-0.67

 Stud

-0.66

elsen

-0.66

iths

-0.64

POSITIVE LOGITS

Buyable

0.95

 innocuous

0.94

icably

0.87

©¶æ¥µ

0.80

 metic

0.78

 contrad

0.78

 unint

0.78

çľ

0.77

 discrep

0.77

\\\\\\\\

0.76

Activations Density 0.004%

the word "seemingly" appearing in the text

the word "seemingly" and expressions indicating a perception versus reality distinction

No Comments

No Known Activations