INDEX

Explanations

explicit mentions of resolutions being voted on or passed

oai_token-act-pair · gpt-3.5-turbo

terms related to legislative actions or proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ocent

-0.70

iott

-0.67

owler

-0.66

ATA

-0.66

inen

-0.64

rium

-0.63

endon

-0.63

gone

-0.63

herty

-0.63

LLOW

-0.62

POSITIVE LOGITS

 resolutions

0.99

 resolution

0.98

 Resolution

0.95

 authorizing

0.84

mary

0.82

xual

0.72

olution

0.69

ancing

0.68

 resolves

0.67

zes

0.66

Activations Density 0.014%

explicit mentions of resolutions being voted on or passed

terms related to legislative actions or proposals

No Comments

No Known Activations