INDEX

Explanations

words related to specific individuals or proper nouns

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of "St," likely indicating a specific subject or context related to a series of events or narratives

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ļéĨĴ

-0.86

hound

-0.75

EStream

-0.75

hower

-0.72

vernment

-0.70

é¾įåĸļå£«

-0.67

 deaf

-0.64

merce

-0.64

 "$:/

-0.62

 friendly

-0.60

POSITIVE LOGITS

uffed

1.22

rict

1.18

itched

1.12

ructure

1.10

upid

1.08

uart

1.07

amped

1.07

alker

1.07

oppable

1.05

ocking

1.04

Activations Density 0.035%

words related to specific individuals or proper nouns

the repeated mention of "St," likely indicating a specific subject or context related to a series of events or narratives

No Comments

No Known Activations