INDEX

Explanations

sentences starting with "When" or similar conjunctions that introduce a condition or event

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "When I"

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

 workaround

-0.80

 sidelines

-0.66

etheless

-0.65

 exception

-0.62

¬¼

-0.62

pac

-0.61

 bailout

-0.60

ishly

-0.59

 regulator

-0.59

 overboard

-0.59

POSITIVE LOGITS

 however

0.71

ourning

0.67

 Camer

0.64

 THEN

0.63

ilib

0.63

 Ammo

0.63

Gall

0.59

eneg

0.59

 Ambro

0.59

 Gleaming

0.59

Activations Density 0.297%

sentences starting with "When" or similar conjunctions that introduce a condition or event

occurrences of the phrase "When I"

No Comments

No Known Activations