INDEX

Explanations

names of political figures and terms related to them

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

istically

-0.74

å£«

-0.74

åĬ

-0.73

ashtra

-0.72

 Hastings

-0.71

icity

-0.70

EMBER

-0.70

RAW

-0.69

utherford

-0.69

OPLE

-0.69

POSITIVE LOGITS

kens

0.94

wana

0.77

bles

0.76

kered

0.75

wash

0.74

bled

0.74

yip

0.74

virt

0.71

pload

0.71

bah

0.71

Activations Density 0.031%

names of political figures and terms related to them

proper nouns, particularly names and locations

No Comments

No Known Activations