INDEX

Explanations

words related to cause and effect

oai_token-act-pair · gpt-3.5-turbo

coordinating conjunctions, particularly "and," often in the context of lists or connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ternity

-0.75

meric

-0.71

 Consent

-0.69

è£ħ

-0.68

ajor

-0.65

REDACTED

-0.65

utor

-0.64

Solid

-0.64

lock

-0.64

 unconditional

-0.63

POSITIVE LOGITS

 thereby

1.04

 thus

0.87

 reduce

0.78

 consequently

0.76

 drain

0.74

 injuring

0.72

 eliminate

0.72

 shorten

0.72

 resulting

0.72

 threaten

0.71

Activations Density 0.558%

words related to cause and effect

coordinating conjunctions, particularly "and," often in the context of lists or connections between ideas

No Comments

No Known Activations