INDEX

Explanations

words related to the perception of someone being well-liked, respected, or influential

oai_token-act-pair · gpt-3.5-turbo

terms related to popularity and respect within a community or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Carnival

-0.65

 Tsukuyomi

-0.64

 Solutions

-0.61

 Conce

-0.59

olutions

-0.59

Failure

-0.58

Wr

-0.57

 flurry

-0.57

 Oops

-0.57

 evasion

-0.57

POSITIVE LOGITS

 amongst

1.27

 among

1.20

among

0.97

 within

0.94

 internationally

0.92

 nationally

0.92

 stature

0.88

 admire

0.86

 abroad

0.85

 throughout

0.84

Activations Density 0.328%

words related to the perception of someone being well-liked, respected, or influential

terms related to popularity and respect within a community or organization

No Comments

No Known Activations