INDEX

Explanations

names of news outlets or media organizations

oai_token-act-pair · gpt-3.5-turbo

specific entity names or acronyms, particularly in a news context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

FML

-0.66

 pand

-0.65

tons

-0.63

generic

-0.62

mas

-0.60

orate

-0.59

iggurat

-0.59

 stockpile

-0.59

wikipedia

-0.58

 strengths

-0.58

POSITIVE LOGITS

 reporter

1.26

 correspondent

1.10

 reporters

1.07

 Reporter

1.06

 magazine

1.04

 News

1.03

 columnist

1.03

 Magazine

1.02

 Newsp

0.94

 Radio

0.94

Activations Density 0.126%

names of news outlets or media organizations

specific entity names or acronyms, particularly in a news context

No Comments

No Known Activations