INDEX

Explanations

locations or directions indicated by the word "near"

oai_token-act-pair · gpt-3.5-turbo

the word "near" in various contexts, indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

zb

-0.79

Upload

-0.78

STATE

-0.75

ilus

-0.75

Wire

-0.73

NT

-0.73

glers

-0.73

uese

-0.72

artz

-0.71

HT

-0.71

POSITIVE LOGITS

sighted

1.01

 vicinity

0.90

 proximity

0.81

qus

0.79

 near

0.77

 nearer

0.77

 Bethlehem

0.76

shore

0.76

oreal

0.74

 contiguous

0.74

Activations Density 0.022%

locations or directions indicated by the word "near"

the word "near" in various contexts, indicating proximity or closeness

No Comments

No Known Activations