INDEX

Explanations

phrases indicating a decision or action to be taken

oai_token-act-pair · gpt-3.5-turbo

statements that begin with the word "Whatever."

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

por

-0.90

ea

-0.90

iard

-0.88

enberg

-0.80

ãĥ¼ãĥ³

-0.79

enburg

-0.78

eds

-0.76

arah

-0.75

arie

-0.74

press

-0.73

POSITIVE LOGITS

 else

1.10

soever

0.98

THING

0.93

 floats

0.88

theless

0.87

body

0.84

 transpired

0.80

 happens

0.78

 happened

0.77

lihood

0.75

Activations Density 0.011%

phrases indicating a decision or action to be taken

statements that begin with the word "Whatever."

No Comments

No Known Activations