INDEX

Explanations

the word "Red" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Red" 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 @ 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

ILA

-0.81

Ö¼

-0.81

-0.79

merce

-0.79

gerald

-0.78

uador

-0.75

FAULT

-0.74

SPONSORED

-0.74

Ó

-0.73

[];

-0.72

POSITIVE LOGITS

eem

1.12

uces

1.10

oubt

1.08

ucing

1.06

neck

1.01

ucer

1.01

Sox

0.99

emption

0.97

uced

0.94

efined

0.92

Activations Density 0.015%

the word "Red" in various contexts

instances of the word "Red" in various contexts

No Comments

No Known Activations