INDEX

Explanations

words related to specific locations or places with a focus on legal or administrative contexts, potentially involving legal issues or administrative actions

oai_token-act-pair · gpt-3.5-turbo

specific geographical locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 holiest

-0.71

 tread

-0.69

Rs

-0.68

 smuggled

-0.68

 declass

-0.67

 Ramadan

-0.67

 Osama

-0.66

 brisk

-0.64

 bestselling

-0.64

 centrif

-0.63

POSITIVE LOGITS

 County

1.47

burgh

1.15

ville

1.11

sylvania

1.08

 Valley

1.08

nesota

1.06

 Rapids

1.04

 Island

1.04

dale

1.03

shire

1.03

Activations Density 0.242%

words related to specific locations or places with a focus on legal or administrative contexts, potentially involving legal issues or administrative actions

specific geographical locations and names

No Comments

No Known Activations