INDEX

Explanations

phrases related to political figures and government actions

oai_token-act-pair · gpt-3.5-turbo

the end of text marker

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ueless

-0.68

ãĤ¦ãĤ¹

-0.66

ttes

-0.60

ãĥ¼ãĥĨ

-0.58

ratch

-0.57

 Siber

-0.57

example

-0.56

xxxx

-0.55

ividual

-0.55

schild

-0.54

POSITIVE LOGITS

 analyst

0.71

 criticised

0.71

UTERS

0.70

 spokesman

0.69

 officials

0.69

 agrees

0.65

 watchdog

0.64

 warns

0.64

 deputy

0.64

 approves

0.63

Activations Density 0.459%

phrases related to political figures and government actions

the end of text marker

No Comments

No Known Activations