INDEX

Explanations

references to legislative actions or decisions

oai_token-act-pair · gpt-3.5-turbo

phrases related to congressional actions and legislative processes

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

ãĤ¨ãĥ«

-0.75

 intangible

-0.70

uni

-0.68

Atl

-0.67

 gradient

-0.67

 crystals

-0.67

 decomp

-0.66

obar

-0.66

 coma

-0.65

mul

-0.65

POSITIVE LOGITS

 convened

1.04

 unanimously

0.99

 recess

0.98

 hearings

0.96

Senate

0.96

 Subcommittee

0.96

 adjourn

0.96

 Appropriations

0.95

 Caucus

0.95

 Majority

0.94

Activations Density 0.458%

references to legislative actions or decisions

phrases related to congressional actions and legislative processes

No Comments

No Known Activations