INDEX

Explanations

names of political figures and locations

oai_token-act-pair · gpt-3.5-turbo

the letter "s" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Shock

-0.66

yz

-0.66

sie

-0.64

yk

-0.62

CVE

-0.61

Els

-0.61

Osc

-0.60

PN

-0.59

ov

-0.59

Alert

-0.58

POSITIVE LOGITS

etheless

0.98

wered

0.92

pecially

0.82

 grandson

0.80

ensibly

0.78

outhern

0.77

 successor

0.77

 oldest

0.76

ources

0.75

uddenly

0.75

Activations Density 0.184%

names of political figures and locations

the letter "s" in various contexts

No Comments

No Known Activations