INDEX

Explanations

phrases expressing a lack of clarity or decisiveness

oai_token-act-pair · gpt-3.5-turbo

negations or expressions of uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

attery

-0.76

 unintended

-0.66

noxious

-0.64

ription

-0.62

 sudden

-0.61

enture

-0.61

ously

-0.60

 Authors

-0.60

 unsu

-0.60

Ĥİ

-0.58

POSITIVE LOGITS

pees

0.88

icable

0.78

 satisf

0.78

shake

0.77

 solved

0.76

 fully

0.75

 reconcil

0.75

hing

0.75

 convinced

0.73

 comprehend

0.70

Activations Density 0.079%

phrases expressing a lack of clarity or decisiveness

negations or expressions of uncertainty

No Comments

No Known Activations