INDEX

Explanations

keywords related to exploring or explaining

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "explore" or its variations

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

 Nadu

-0.71

chery

-0.67

WAYS

-0.65

interstitial

-0.64

DEN

-0.64

maid

-0.63

pora

-0.62

grass

-0.62

ndra

-0.62

 Confederacy

-0.61

POSITIVE LOGITS

oded

1.15

oding

1.13

oit

1.12

icit

1.08

ained

1.04

osion

1.04

orative

1.02

odes

1.02

orer

1.02

acements

1.01

Activations Density 0.016%

keywords related to exploring or explaining

occurrences of the word "explore" or its variations

No Comments

No Known Activations