INDEX

Explanations

Twitter handles

oai_token-act-pair · gpt-3.5-turbo

Twitter handles or user mentions

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

 elect

-0.77

 Malk

-0.77

 orche

-0.72

 Starr

-0.69

 frig

-0.68

 stricken

-0.67

Vie

-0.66

 rust

-0.65

 ordinance

-0.65

 intox

-0.64

POSITIVE LOGITS

#$

1.04

(@

0.99

usage

0.89

username

0.88

deck

0.86

hello

0.80

usr

0.79

tip

0.78

sorry

0.78

updated

0.77

Activations Density 0.012%

Twitter handles

Twitter handles or user mentions

No Comments

No Known Activations