INDEX

Explanations

references to droplets

oai_token-act-pair · gpt-3.5-turbo

mentions of droplets—and possibly related quantifiable forms of liquid

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

 Canary

-0.82

 Blessed

-0.77

 Trident

-0.72

ãĥĨãĤ£

-0.72

 specificity

-0.72

 Catalyst

-0.69

 Clause

-0.69

Ou

-0.69

ãĥķãĤ©

-0.68

 à¨

-0.68

POSITIVE LOGITS

plets

1.33

plet

1.29

ppers

1.19

pper

1.09

ppings

1.08

ves

1.02

vable

0.90

quet

0.90

opa

0.89

ids

0.88

Activations Density 0.022%

references to droplets

mentions of droplets—and possibly related quantifiable forms of liquid

No Comments

No Known Activations