INDEX

Explanations

words related to locations or places, often including distances and directions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word 'ind'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itton

-0.72

xit

-0.68

senal

-0.66

 depreciation

-0.63

 tremend

-0.62

prus

-0.62

avorite

-0.61

ngth

-0.60

 compr

-0.59

iannopoulos

-0.59

POSITIVE LOGITS

erella

1.17

icative

1.16

ebted

1.13

irect

1.11

sight

1.09

icator

1.07

ividually

1.01

icators

0.99

ications

0.98

Activations Density 0.018%

words related to locations or places, often including distances and directions

occurrences of the word 'ind'

No Comments

No Known Activations