INDEX

Explanations

extended phrases containing a verb "said"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

otion

-0.76

xtap

-0.74

pleting

-0.71

email

-0.68

\/\/

-0.68

physical

-0.67

oppable

-0.67

EMBER

-0.67

amac

-0.65

Issue

-0.64

POSITIVE LOGITS

 goodbye

0.84

 yesterday

0.73

 bluntly

0.68

 aloud

0.63

 repeatedly

0.62

 Monday

0.62

 Wednesday

0.61

 earlier

0.60

 Tuesday

0.60

 emphatically

0.59

Activations Density 0.191%

extended phrases containing a verb "said"

instances of the word "said."

No Comments

No Known Activations