INDEX

Explanations

phrases related to events or actions that will not repeat or occur again

oai_token-act-pair · gpt-3.5-turbo

repeated references to the word "again."

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

catentry

-0.78

 gist

-0.68

maxwell

-0.65

yip

-0.61

 median

-0.61

âĸĳâĸĳ

-0.61

 proxy

-0.60

 asymm

-0.59

 differential

-0.59

Definition

-0.58

POSITIVE LOGITS

nor

0.87

theless

0.85

 unless

0.74

 until

0.73

ankind

0.71

until

0.70

atile

0.68

 dime

0.66

unless

0.66

 till

0.66

Activations Density 0.066%

phrases related to events or actions that will not repeat or occur again

repeated references to the word "again."

No Comments

No Known Activations