INDEX

Explanations

phrases related to communication or indication

oai_token-act-pair · gpt-3.5-turbo

terms related to signaling or indications of intent or behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

frey

-0.75

 Chatt

-0.74

atl

-0.72

atche

-0.71

sm

-0.71

ratch

-0.70

jan

-0.70

peg

-0.70

enne

-0.70

anu

-0.70

POSITIVE LOGITS

 signs

0.98

 signaling

0.91

 Signs

0.90

 signals

0.90

 departure

0.83

 signaled

0.83

 signalling

0.82

 departures

0.81

 allegiance

0.80

 warnings

0.80

Activations Density 0.030%

phrases related to communication or indication

terms related to signaling or indications of intent or behavior

No Comments

No Known Activations