INDEX

Explanations

references to speeches given by various individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "speech."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

involved

-0.71

rome

-0.59

 Coast

-0.58

 Trout

-0.57

 Construct

-0.56

 exploited

-0.55

 Soldiers

-0.54

 Lantern

-0.54

 saline

-0.54

 Rover

-0.54

POSITIVE LOGITS

writer

0.91

writers

0.90

 speeches

0.89

 speech

0.87

 Speech

0.83

speech

0.82

writing

0.78

heit

0.78

boxing

0.73

gow

0.73

Activations Density 0.038%

references to speeches given by various individuals

instances of the word "speech."

No Comments

No Known Activations