INDEX

Explanations

phrases indicating assumptions, conjectures, or speculations

oai_token-act-pair · gpt-3.5-turbo

phrases that express assumptions or conjectures about past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

pour

-0.67

jri

-0.67

opian

-0.66

pie

-0.63

iard

-0.63

heres

-0.62

ettle

-0.59

ãĤŃ

-0.58

patch

-0.58

 Griff

-0.58

POSITIVE LOGITS

 kidding

0.87

 wonder

0.73

 sensed

0.71

 Wond

0.67

 pity

0.66

©¶æ

0.66

 somewhere

0.62

ones

0.61

 wondering

0.61

 Scream

0.61

Activations Density 0.106%

phrases indicating assumptions, conjectures, or speculations

phrases that express assumptions or conjectures about past events

No Comments

No Known Activations