INDEX

Explanations

phrases related to work and labor conditions

oai_token-act-pair · gpt-3.5-turbo

phrases related to adverse effects and medical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Truth

-0.89

erest

-0.89

nesday

-0.88

 ðŁĻĤ

-0.88

ruary

-0.87

NAS

-0.83

soType

-0.82

fuck

-0.82

ultimate

-0.82

 ðŁĺ

-0.81

POSITIVE LOGITS

 dozens

1.07

 varying

1.07

 makeshift

1.06

 rudimentary

1.05

 roadside

1.05

 sophisticated

1.00

 myriad

0.99

 specialized

0.97

 frequent

0.97

 elaborate

0.97

Activations Density 0.732%

phrases related to work and labor conditions

phrases related to adverse effects and medical issues

No Comments

No Known Activations