INDEX

Explanations

instances where someone or something is facing criticism or scrutiny

oai_token-act-pair · gpt-3.5-turbo

references to being criticized or scrutinized, particularly in a political or social context

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

 cures

-0.68

 Nope

-0.65

ogo

-0.64

 vantage

-0.63

 cure

-0.61

uana

-0.61

olute

-0.60

 Alive

-0.60

abiding

-0.60

entry

-0.60

POSITIVE LOGITS

 accusations

0.86

 allegations

0.85

 lately

0.81

 alleging

0.79

 controversy

0.77

 controversies

0.76

 recently

0.76

 controvers

0.75

 criticism

0.74

 accusing

0.74

Activations Density 0.163%

instances where someone or something is facing criticism or scrutiny

references to being criticized or scrutinized, particularly in a political or social context

No Comments

No Known Activations