INDEX

Explanations

words related to being random, based on a selection of arbitrary values or actions

oai_token-act-pair · gpt-3.5-turbo

references to arbitrary standards or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iosis

-0.84

oir

-0.83

iquette

-0.81

icans

-0.81

iano

-0.80

din

-0.78

ieri

-0.77

iao

-0.77

iens

-0.77

iere

-0.75

POSITIVE LOGITS

 whims

0.88

 arbitrary

0.87

 guiActiveUn

0.83

 whim

0.77

 arbitrarily

0.77

 recomp

0.75

judicial

0.72

 bystand

0.71

 guessing

0.71

 gratification

0.70

Activations Density 0.024%

words related to being random, based on a selection of arbitrary values or actions

references to arbitrary standards or decisions

No Comments

No Known Activations