INDEX

Explanations

references to retail stores

oai_token-act-pair · gpt-3.5-turbo

references to "store" in various contexts

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

vous

-0.79

vernment

-0.79

SHIP

-0.77

ersen

-0.77

 Caucus

-0.69

theless

-0.69

emonic

-0.69

iferation

-0.66

inx

-0.66

param

-0.65

POSITIVE LOGITS

 shelves

1.11

houses

1.00

store

0.95

house

0.92

front

0.90

rooms

0.90

 store

0.88

 clerk

0.88

keeper

0.87

 clerks

0.87

Activations Density 0.028%

references to retail stores

references to "store" in various contexts

No Comments

No Known Activations