INDEX

Explanations

keywords related to potential or anticipated outcomes

oai_token-act-pair · gpt-3.5-turbo

mentions of "prospects" or potential future outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Favorite

-0.67

tein

-0.65

AKING

-0.61

cipl

-0.60

Flow

-0.59

zip

-0.58

pmwiki

-0.56

weed

-0.56

ASED

-0.55

aundering

-0.54

POSITIVE LOGITS

ively

0.96

llor

0.90

ures

0.88

ours

0.85

ors

0.83

uring

0.81

orial

0.80

uses

0.77

 horizon

0.77

ually

0.75

Activations Density 0.036%

keywords related to potential or anticipated outcomes

mentions of "prospects" or potential future outcomes

No Comments

No Known Activations