INDEX

Explanations

words related to sudden increases or rises in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of increases and upticks in various statistics or trends

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

 wisely

-0.73

 mates

-0.72

 curls

-0.71

agine

-0.70

wered

-0.68

 yours

-0.67

 someday

-0.66

 sacrific

-0.66

Reviewed

-0.65

 buddies

-0.65

POSITIVE LOGITS

 uptick

0.94

 deterioration

0.93

 trend

0.92

 spate

0.89

 resurgence

0.85

 concerted

0.83

 exodus

0.83

 worsening

0.80

 decline

0.79

 epidemic

0.79

Activations Density 0.287%

words related to sudden increases or rises in various contexts

occurrences of increases and upticks in various statistics or trends

No Comments

No Known Activations