INDEX

Explanations

words related to the concept of 'lion'

oai_token-act-pair · gpt-3.5-turbo

mentions of locations or geographic identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Administ

-0.79

elect

-0.76

Nap

-0.73

INO

-0.71

LECT

-0.71

 Compton

-0.70

ANCE

-0.69

ELD

-0.69

ummer

-0.68

icka

-0.68

POSITIVE LOGITS

 embryos

0.90

 slaughtered

0.80

 herds

0.80

 eggs

0.77

 leukemia

0.74

beans

0.74

 animals

0.74

 kingdom

0.73

 larvae

0.72

 mosquit

0.71

Activations Density 0.199%

words related to the concept of 'lion'

mentions of locations or geographic identifiers

No Comments

No Known Activations