INDEX

Explanations

terms related to showrunners and important milestones

oai_token-act-pair · gpt-3.5-turbo

terms related to roles, particularly in the context of showrunners and milestone events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Nap

-0.75

EX

-0.73

ħ

-0.71

į

-0.70

¾

-0.70

hold

-0.69

VPN

-0.69

ĨĴ

-0.68

NL

-0.68

²

-0.68

POSITIVE LOGITS

oldemort

0.81

sers

0.76

worthiness

0.73

phrine

0.73

 Aviv

0.71

sbm

0.70

aukee

0.70

itis

0.68

opathy

0.65

 pageant

0.64

Activations Density 0.149%

terms related to showrunners and important milestones

terms related to roles, particularly in the context of showrunners and milestone events

No Comments

No Known Activations