INDEX

Explanations

adjectives and past participles indicating loss or disappearance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lost" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ansky

-0.73

osi

-0.71

sis

-0.69

erity

-0.69

INC

-0.66

utical

-0.65

 prepared

-0.64

ERAL

-0.64

udos

-0.63

NVIDIA

-0.63

POSITIVE LOGITS

 Souls

0.98

 souls

0.94

erness

0.78

lust

0.78

luster

0.78

 innocence

0.77

 sight

0.77

hearted

0.76

MH

0.72

orage

0.69

Activations Density 0.027%

adjectives and past participles indicating loss or disappearance

instances of the word "lost" in various contexts

No Comments

No Known Activations