INDEX

Explanations

phrases related to being restricted or confined in a specific location

oai_token-act-pair · gpt-3.5-turbo

phrases related to confinement or being restricted

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

enegger

-0.80

alis

-0.76

gomery

-0.71

CAST

-0.69

ãĥĳ

-0.67

anmar

-0.66

JC

-0.65

ãĤ¡

-0.64

aster

-0.64

athy

-0.64

POSITIVE LOGITS

 knots

0.84

 wrists

0.75

 throats

0.73

 leash

0.73

hold

0.72

 Borders

0.70

 tight

0.70

 tightly

0.69

 contracts

0.67

 ankles

0.67

Activations Density 0.110%

phrases related to being restricted or confined in a specific location

phrases related to confinement or being restricted

No Comments

No Known Activations