INDEX

Explanations

mentions of political or influential leaders

oai_token-act-pair · gpt-3.5-turbo

references to political leaders across various contexts

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

ITNESS

-0.71

nery

-0.66

INGTON

-0.65

Prev

-0.65

CO

-0.64

riv

-0.61

Wo

-0.61

ATIONAL

-0.60

ALLY

-0.60

LV

-0.60

POSITIVE LOGITS

hips

1.15

hip

1.09

doms

0.98

paces

0.80

cius

0.80

stration

0.79

 negotiator

0.77

pin

0.73

mith

0.73

wcs

0.73

Activations Density 0.047%

mentions of political or influential leaders

references to political leaders across various contexts

No Comments

No Known Activations