INDEX

Explanations

references to the material "tar"

oai_token-act-pair · gpt-3.5-turbo

references to tar and its related contexts

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

 Startup

-0.88

alian

-0.87

guyen

-0.86

nesota

-0.86

iren

-0.85

ĨĴ

-0.84

ļéĨĴ

-0.84

braska

-0.82

ervation

-0.81

entric

-0.81

POSITIVE LOGITS

tar

1.12

 sands

0.91

ãĥ£

0.82

 smear

0.79

pee

0.75

spl

0.75

balls

0.73

 flares

0.71

ril

0.71

 blob

0.69

Activations Density 0.027%

references to the material "tar"

references to tar and its related contexts

No Comments

No Known Activations