INDEX

Explanations

numbers related to news articles

oai_token-act-pair · gpt-3.5-turbo

references to numerical data or statistics

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

waves

-0.73

undai

-0.73

efficients

-0.71

perm

-0.70

raltar

-0.68

ularity

-0.68

 neighb

-0.66

ibility

-0.65

cible

-0.65

oppy

-0.65

POSITIVE LOGITS

1.05

0.88

0.77

0.76

hof

0.75

Â¢

0.74

RD

0.73

APH

0.73

Activations Density 0.037%

numbers related to news articles

references to numerical data or statistics

No Comments

No Known Activations