INDEX

Explanations

names of specific places or institutions

oai_token-act-pair · gpt-3.5-turbo

references to specific institutions, locations, and professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

rencies

-0.71

vot

-0.61

 validity

-0.60

morrow

-0.59

 defin

-0.58

reek

-0.56

Weak

-0.56

 Recommend

-0.56

currently

-0.55

Item

-0.54

POSITIVE LOGITS

 helm

0.93

 stint

0.90

 firsthand

0.83

 obscurity

0.71

ukemia

0.71

orld

0.70

 navigating

0.70

 volunteering

0.69

anship

0.69

 spotlight

0.69

Activations Density 0.371%

names of specific places or institutions

references to specific institutions, locations, and professional contexts

No Comments

No Known Activations