INDEX

Explanations

terms related to authority, control, or supervision

oai_token-act-pair · gpt-3.5-turbo

references to legal contexts or regulations

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

uckland

-0.81

ocre

-0.79

utonium

-0.70

 belie

-0.69

ffield

-0.67

ffen

-0.67

elong

-0.67

ument

-0.64

essen

-0.64

enes

-0.63

POSITIVE LOGITS

 ausp

1.10

ħĭ

1.00

 guise

1.00

 supervision

0.92

 microscope

0.88

 Radar

0.81

 circumstances

0.81

ĨĴ

0.79

ctory

0.78

 conditions

0.75

Activations Density 0.158%

terms related to authority, control, or supervision

references to legal contexts or regulations

No Comments

No Known Activations