INDEX

Explanations

words related to physical locations or structures

oai_token-act-pair · gpt-3.5-turbo

words related to "core" or "core concepts."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endor

-0.85

 Order

-0.68

 Honour

-0.66

enstein

-0.65

 Sacrament

-0.65

leck

-0.65

 Guilty

-0.65

 Disorder

-0.64

hirt

-0.64

hran

-0.64

POSITIVE LOGITS

nered

1.07

vette

0.89

fman

0.87

rection

0.85

bons

0.81

pling

0.81

ption

0.79

nea

0.79

ocular

0.78

aling

0.77

Activations Density 0.027%

words related to physical locations or structures

words related to "core" or "core concepts."

No Comments

No Known Activations