INDEX

Explanations

correlating facts or concepts within a set of data

oai_token-act-pair · gpt-3.5-turbo

phrases or statements indicating the existence or presence of concepts or entities

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

tal

-0.72

itiz

-0.70

phasis

-0.63

obook

-0.62

luaj

-0.60

 methodology

-0.59

phas

-0.59

iT

-0.58

mol

-0.58

ipop

-0.57

POSITIVE LOGITS

 respectively

1.77

 alike

1.61

depending

0.88

 jointly

0.85

 interchangeable

0.85

 simultaneously

0.79

 intertwined

0.79

 fronts

0.77

 together

0.74

 insepar

0.74

Activations Density 0.310%

correlating facts or concepts within a set of data

phrases or statements indicating the existence or presence of concepts or entities

No Comments

No Known Activations