INDEX

Explanations

locations in Washington, D.C

oai_token-act-pair · gpt-3.5-turbo

the city name and its abbreviation for Washington, D.C

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 chopping

-0.71

 sidel

-0.71

 mant

-0.71

 acron

-0.71

 retrospective

-0.61

 liquid

-0.60

 increasing

-0.60

 rule

-0.59

 frameworks

-0.58

 roundup

-0.58

POSITIVE LOGITS

Va

1.06

town

0.77

sylvania

0.74

essee

0.71

rex

0.70

lux

0.70

apolis

0.69

edu

0.68

western

0.68

Activations Density 0.036%

locations in Washington, D.C

the city name and its abbreviation for Washington, D.C

No Comments

No Known Activations