INDEX

Explanations

single words starting with 'LE'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "LE" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 indemn

-0.62

Rus

-0.62

 Heat

-0.61

den

-0.59

Pak

-0.59

 folk

-0.58

ific

-0.58

 vict

-0.57

 Broadcasting

-0.56

 sickness

-0.56

POSITIVE LOGITS

LE

4.04

LES

2.19

LET

2.00

le

1.90

LED

1.54

LE

1.52

lement

1.47

LECT

1.46

LER

1.44

les

1.41

Activations Density 0.014%

single words starting with 'LE'

occurrences of the word "LE" across various contexts

No Comments

No Known Activations