INDEX

Explanations

statements related to public policy

oai_token-act-pair · gpt-3.5-turbo

terms related to policy and policy-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

htaking

-0.74

 Stain

-0.72

eneg

-0.72

 Templ

-0.72

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.72

Ago

-0.70

raction

-0.70

bane

-0.69

azar

-0.69

ITNESS

-0.67

POSITIVE LOGITS

 policy

1.09

policy

1.01

 policies

1.01

 makers

1.01

 prescriptions

0.98

making

0.95

 interventions

0.90

 policymakers

0.90

makers

0.88

 initiatives

0.87

Activations Density 0.022%

statements related to public policy

terms related to policy and policy-making processes

No Comments

No Known Activations