INDEX

Explanations

references to the concept of "anything."

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of the word "anything" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

irth

-0.77

ros

-0.76

grad

-0.74

nec

-0.70

pa

-0.69

inst

-0.66

hap

-0.64

 anonymity

-0.63

ritz

-0.63

lav

-0.63

POSITIVE LOGITS

 else

1.53

Else

1.39

THING

1.23

 imaginable

1.08

 Else

1.04

 remotely

1.02

 resembling

0.93

 conceivable

0.88

 whatsoever

0.85

soever

0.81

Activations Density 0.019%

references to the concept of "anything."

repetitive mentions of the word "anything" in various contexts

No Comments

No Known Activations