INDEX

Explanations

references to smoke

oai_token-act-pair · gpt-3.5-turbo

references to smoke 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Volt

-0.72

":["

-0.69

HCR

-0.66

*/(

-0.65

 mathematic

-0.64

eanor

-0.62

onomous

-0.60

emort

-0.59

irlf

-0.58

 Vanguard

-0.58

POSITIVE LOGITS

 smoke

1.10

 Smoke

1.05

crow

0.84

 smokes

0.82

lake

0.82

 haze

0.81

 smoked

0.81

pipe

0.80

creen

0.78

 smoking

0.78

Activations Density 0.011%

references to smoke

references to smoke in various contexts

No Comments

No Known Activations