INDEX

Explanations

references to medical conditions or terminology, especially those related to body parts or processes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "od" and its variations

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

Ago

-0.67

 Leone

-0.62

_>

-0.62

vant

-0.61

kson

-0.60

Ana

-0.60

 Faul

-0.57

Ki

-0.57

UGE

-0.55

Has

-0.55

POSITIVE LOGITS

yssey

1.35

ragon

1.04

rome

1.03

iox

1.03

iamond

1.00

iversity

0.99

sworth

0.96

iazep

0.94

ouble

0.93

iscover

0.93

Activations Density 0.035%

references to medical conditions or terminology, especially those related to body parts or processes

instances of the word "od" and its variations

No Comments

No Known Activations