INDEX

Explanations

references to something being officially released or made available to the public

oai_token-act-pair · gpt-3.5-turbo

instances of the word "published."

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

llan

-0.87

uppet

-0.72

Ĭ±

-0.69

 awakened

-0.69

aura

-0.69

xa

-0.68

ggle

-0.67

aturation

-0.67

hart

-0.66

vette

-0.66

POSITIVE LOGITS

lishing

1.11

lisher

1.06

 excerpts

0.92

lishes

0.84

 publication

0.71

Ð»

0.70

 exploits

0.69

 Journals

0.69

 publishing

0.68

itatively

0.68

Activations Density 0.041%

references to something being officially released or made available to the public

instances of the word "published."

No Comments

No Known Activations