INDEX

Explanations

references to executive orders and actions

oai_token-act-pair · gpt-3.5-turbo

references to executive actions or orders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ulia

-0.78

cale

-0.72

Else

-0.71

Prev

-0.70

ERO

-0.69

atoon

-0.69

apo

-0.69

selves

-0.69

 Poles

-0.68

Pause

-0.67

POSITIVE LOGITS

utive

1.14

 executive

0.99

stration

0.87

 branch

0.85

 summary

0.83

 committee

0.81

 officer

0.78

utions

0.76

 chef

0.75

 chairman

0.74

Activations Density 0.015%

references to executive orders and actions

references to executive actions or orders

No Comments

No Known Activations