INDEX

Explanations

scientific or research-related terms related to evidence

oai_token-act-pair · gpt-3.5-turbo

references to different types of evidence in a discussion or argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

eteria

-0.83

iery

-0.74

iries

-0.66

aughs

-0.65

 Massacre

-0.63

 expense

-0.59

lasses

-0.59

 Tune

-0.58

 Victims

-0.58

nell

-0.58

POSITIVE LOGITS

 suggesting

1.18

 linking

1.16

 demonstrating

1.11

 indicating

1.09

 showing

1.06

 supporting

1.05

 proving

1.01

 that

0.95

 documenting

0.93

 confirming

0.91

Activations Density 0.092%

scientific or research-related terms related to evidence

references to different types of evidence in a discussion or argument

No Comments

No Known Activations