INDEX

Explanations

words related to authority figures or leaders in a hierarchical structure

oai_token-act-pair · gpt-3.5-turbo

references to "boss" characters or roles in various contexts, particularly in video games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Pwr

-0.82

 Scotia

-0.81

ctica

-0.67

CTR

-0.65

 Trails

-0.64

leigh

-0.63

 flares

-0.62

Interstitial

-0.62

lihood

-0.61

 Archives

-0.60

POSITIVE LOGITS

olean

0.87

anova

0.87

enger

0.86

heet

0.80

nuts

0.80

es

0.79

ulas

0.79

ery

0.78

hips

0.77

nut

0.76

Activations Density 0.022%

words related to authority figures or leaders in a hierarchical structure

references to "boss" characters or roles in various contexts, particularly in video games

No Comments

No Known Activations