INDEX

Explanations

words related to specific locations or areas

oai_token-act-pair · gpt-3.5-turbo

terms related to specific zones or areas, particularly in geographical or thematic contexts

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utive

-0.84

anooga

-0.82

NECT

-0.79

issance

-0.77

sonian

-0.74

lycer

-0.71

thora

-0.71

tons

-0.70

FUL

-0.69

bats

-0.69

POSITIVE LOGITS

 zones

1.04

 zone

1.03

 dwell

0.89

 Areas

0.85

 deline

0.82

 boundary

0.81

 area

0.81

 adjoining

0.79

 areas

0.78

 boundaries

0.77

Activations Density 0.044%

words related to specific locations or areas

terms related to specific zones or areas, particularly in geographical or thematic contexts

No Comments

No Known Activations