INDEX

Explanations

mentions of news sources like "The Washington Post" followed by specific content or author names

oai_token-act-pair · gpt-3.5-turbo

references to articles or publications, specifically from "The Washington Post."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 whilst

-0.79

 secondly

-0.72

 util

-0.71

-0.68

 enqu

-0.68

 Whilst

-0.65

wards

-0.64

SQ

-0.63

course

-0.63

tons

-0.63

POSITIVE LOGITS

 POLITICO

0.93

 Caption

0.84

CLOSE

0.70

Washington

0.70

 nonpartisan

0.69

ASHINGTON

0.68

Republicans

0.68

CNN

0.67

VERTISEMENT

0.67

 Washington

0.66

Activations Density 0.253%

mentions of news sources like "The Washington Post" followed by specific content or author names

references to articles or publications, specifically from "The Washington Post."

No Comments

No Known Activations