INDEX

Explanations

terms related to online content, especially within a governmental context

oai_token-act-pair · gpt-3.5-turbo

mentions of websites or online resources

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

lect

-0.73

redo

-0.69

fort

-0.69

erick

-0.68

iband

-0.68

vind

-0.65

fif

-0.64

oway

-0.64

administ

-0.63

ott

-0.62

POSITIVE LOGITS

chrome

0.80

ãĥ´ãĤ¡

0.65

liest

0.65

rette

0.64

 Marilyn

0.64

amins

0.64

nikov

0.63

rants

0.63

ERY

0.63

umbn

0.63

Activations Density 0.000%

terms related to online content, especially within a governmental context

mentions of websites or online resources

No Comments

No Known Activations