INDEX

Explanations

words related to completion or achievement

oai_token-act-pair · gpt-3.5-turbo

phrases indicating completion or accomplishment

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

ifles

-0.67

eros

-0.65

 recalls

-0.65

Topics

-0.64

regate

-0.62

uzzle

-0.59

 relates

-0.58

amples

-0.57

APH

-0.57

acks

-0.57

POSITIVE LOGITS

going

0.66

ãĥ¼ãĥ«

0.65

Ð¼

0.63

 lately

0.62

rated

0.61

ÃįÃį

0.60

 awfully

0.59

 Calais

0.59

 alright

0.59

 bloom

0.58

Activations Density 0.459%

words related to completion or achievement

phrases indicating completion or accomplishment

No Comments

No Known Activations