INDEX

Explanations

phrases related to first impressions

oai_token-act-pair · gpt-3.5-turbo

instances of phrases that indicate first impressions or appearances

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

icer

-0.77

ammy

-0.72

rus

-0.69

ãĥĺ

-0.67

tailed

-0.67

die

-0.62

 choir

-0.61

lez

-0.60

doms

-0.59

cess

-0.59

POSITIVE LOGITS

 glance

1.04

 blush

0.85

 superf

0.77

 standpoint

0.72

 premise

0.71

 understandable

0.66

 intuitive

0.65

 resembles

0.64

 sounds

0.64

 clues

0.64

Activations Density 0.087%

phrases related to first impressions

instances of phrases that indicate first impressions or appearances

No Comments

No Known Activations