INDEX

Explanations

numbers representing years or dates

oai_token-act-pair · gpt-3.5-turbo

references to specific years and numerical data

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

ivity

-0.86

ivities

-0.86

ãĤ¤ãĥĪ

-0.84

ique

-0.79

icles

-0.75

iques

-0.74

ICLE

-0.74

ional

-0.71

ifact

-0.71

cies

-0.71

POSITIVE LOGITS

 externalToEVAOnly

1.01

0.87

0.80

mph

0.79

0.78

pher

0.78

pha

0.76

IOR

0.76

0.75

Activations Density 0.084%

numbers representing years or dates

references to specific years and numerical data

No Comments

No Known Activations