INDEX

Explanations

references to the city of St. Louis

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of "St. Louis" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

VALUE

-0.86

udeb

-0.82

vana

-0.75

ãĥ¼ãĥ

-0.72

razil

-0.71

cffffcc

-0.70

ãĥĥãĤ¯

-0.67

ãĥ¼ãĤ¯

-0.67

REC

-0.67

irlf

-0.66

POSITIVE LOGITS

 Cardinals

1.04

 Rams

1.04

 County

1.00

 Angeles

0.90

 Rapids

0.84

 Blues

0.84

 Browns

0.83

sburgh

0.81

XIV

0.80

 Slug

0.80

Activations Density 0.018%

references to the city of St. Louis

repeated mentions of "St. Louis" in the text

No Comments

No Known Activations