INDEX

Explanations

the word "Tak" followed by a high numerical value

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Tak"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

afort

-0.81

iths

-0.77

pard

-0.72

ecast

-0.72

cedented

-0.69

sheets

-0.69

umption

-0.68

umn

-0.67

mble

-0.67

ffield

-0.66

POSITIVE LOGITS

UCK

0.82

istani

0.79

ota

0.77

ICLE

0.74

atsuki

0.69

rade

0.69

 Hutchinson

0.68

Ame

0.67

umar

0.67

uning

0.66

Activations Density 0.075%

the word "Tak" followed by a high numerical value

repeated mentions of the name "Tak"

No Comments

No Known Activations