INDEX

Explanations

references to geological features or terms with 'ge' followed by another letter

oai_token-act-pair · gpt-3.5-turbo

terms related to geology and geological concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.72

ABE

-0.69

æł

-0.67

EED

-0.66

ioned

-0.65

ividual

-0.63

INGTON

-0.63

 Norn

-0.62

lain

-0.62

 Carbuncle

-0.61

POSITIVE LOGITS

ographical

1.17

ophysical

1.16

cko

1.13

orgetown

1.12

ographically

1.07

ORGE

1.07

ffen

1.06

othermal

1.06

ologic

1.05

ography

1.04

Activations Density 0.027%

references to geological features or terms with 'ge' followed by another letter

terms related to geology and geological concepts

No Comments

No Known Activations