INDEX

Explanations

phrases describing something as an ideal or with high praise

oai_token-act-pair · gpt-3.5-turbo

the word "perfect" and its variations in different 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

Downloadha

-0.91

SEE

-0.87

ker

-0.82

ktop

-0.81

SAY

-0.78

NetMessage

-0.76

cohol

-0.76

clips

-0.75

strip

-0.74

bane

-0.74

POSITIVE LOGITS

 symmetry

0.83

 encaps

0.78

 harmony

0.78

ions

0.78

 synergy

0.77

 timing

0.76

itude

0.74

 blend

0.74

ion

0.73

 embodiment

0.73

Activations Density 0.020%

phrases describing something as an ideal or with high praise

the word "perfect" and its variations in different contexts

No Comments

No Known Activations