INDEX

Explanations

words related to hydroelectricity or hydrocarbons

oai_token-act-pair · gpt-3.5-turbo

terms related to hydro resources and energy production

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

lihood

-0.77

Reloaded

-0.75

 Breed

-0.74

 Keen

-0.73

 Advent

-0.73

 Garland

-0.71

 Lynch

-0.71

 Cardinals

-0.70

acular

-0.69

Doe

-0.69

POSITIVE LOGITS

carbon

1.20

electric

1.19

cephal

1.18

chlor

1.07

xy

0.95

ulic

0.93

 absor

0.91

static

0.90

colour

0.88

mel

0.88

Activations Density 0.011%

words related to hydroelectricity or hydrocarbons

terms related to hydro resources and energy production

No Comments

No Known Activations