INDEX

Explanations

instances of phrases indicating an excessive amount or extent of something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

inarily

-0.69

smith

-0.65

iens

-0.62

season

-0.58

elfth

-0.57

igi

-0.56

emet

-0.55

 Except

-0.55

 Circuit

-0.55

DIT

-0.55

POSITIVE LOGITS

 much

1.09

 many

1.02

Much

0.87

 Much

0.81

 close

0.77

 Many

0.76

 cheaply

0.76

far

0.75

len

0.75

ls

0.75

Activations Density 0.044%

instances of phrases indicating an excessive amount or extent of something

No Comments

No Known Activations