INDEX

Explanations

adjectives indicating improbability or unlikeliness

oai_token-act-pair · gpt-3.5-turbo

the term "unlikely" in various contexts, indicating skepticism or doubt regarding outcomes or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ulative

-0.91

arte

-0.71

ravings

-0.71

RAFT

-0.71

nan

-0.70

ixed

-0.69

 Economy

-0.69

ricted

-0.69

adan

-0.68

iph

-0.68

POSITIVE LOGITS

 unlikely

1.11

 improbable

1.00

 unanimous

0.85

 fortun

0.80

 underdog

0.80

icably

0.79

lihood

0.79

 mosqu

0.78

 unemploy

0.78

 resil

0.78

Activations Density 0.009%

adjectives indicating improbability or unlikeliness

the term "unlikely" in various contexts, indicating skepticism or doubt regarding outcomes or events

No Comments

No Known Activations