INDEX

Explanations

comparative adjectives

oai_token-act-pair · gpt-3.5-turbo

the word "even" in various contexts emphasizing comparison or degree

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

units

-0.78

mson

-0.77

ATURES

-0.76

artments

-0.76

utics

-0.74

apons

-0.74

unia

-0.72

 Libraries

-0.71

hops

-0.70

 SPORTS

-0.68

POSITIVE LOGITS

 spoiler

0.80

 underdog

0.75

 explanation

0.74

 approximation

0.73

 hitter

0.72

 temper

0.70

 sequel

0.69

 excerpt

0.69

 variant

0.69

 uphill

0.69

Activations Density 0.114%

comparative adjectives

the word "even" in various contexts emphasizing comparison or degree

No Comments

No Known Activations