INDEX

Explanations

phrases where the term "head of" is mentioned

oai_token-act-pair · gpt-3.5-turbo

specific references to leadership positions or titles

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

nee

-0.74

ibe

-0.69

nce

-0.65

nces

-0.64

fair

-0.63

cookie

-0.61

-0.60

ier

-0.60

asta

-0.60

ista

-0.59

POSITIVE LOGITS

 delegation

0.76

 overseeing

0.71

 Household

0.68

²¾

0.68

 staff

0.68

 household

0.66

¥ŀ

0.64

iciary

0.62

ikuman

0.62

 Operations

0.61

Activations Density 0.066%

phrases where the term "head of" is mentioned

specific references to leadership positions or titles

No Comments

No Known Activations