INDEX

Explanations

words related to unexpected or surprising things

oai_token-act-pair · gpt-3.5-turbo

instances of the word "surprisingly" 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

gang

-0.75

flight

-0.72

tein

-0.70

icipated

-0.69

yi

-0.69

glas

-0.66

escription

-0.66

icip

-0.65

amins

-0.65

Ã¨re

-0.63

POSITIVE LOGITS

beit

0.75

 absent

0.75

Effective

0.69

 enough

0.66

 overpowered

0.66

 LIMITED

0.66

STEM

0.66

 surprising

0.64

atility

0.64

 readable

0.64

Activations Density 0.022%

words related to unexpected or surprising things

instances of the word "surprisingly" in various contexts

No Comments

No Known Activations