INDEX

Explanations

sentences talking about future plans or possibilities

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or conditionality

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

rities

-0.66

 Alam

-0.64

plates

-0.63

ãĥ¼ãĥ³

-0.61

robe

-0.61

seys

-0.60

monds

-0.59

styles

-0.59

 stripes

-0.58

 lamps

-0.58

POSITIVE LOGITS

 blat

0.79

 happen

0.76

 happening

0.75

 unintentional

0.72

 happened

0.70

 misunder

0.70

cture

0.69

 happ

0.68

ebin

0.68

 happens

0.67

Activations Density 0.205%

sentences talking about future plans or possibilities

expressions of uncertainty or conditionality

No Comments

No Known Activations