INDEX

Explanations

words related to evaluation or judgment

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to the concept of rating or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

amar

-0.75

 undone

-0.72

auga

-0.64

INS

-0.64

antis

-0.63

ords

-0.63

peria

-0.62

imura

-0.61

itars

-0.61

aina

-0.60

POSITIVE LOGITS

rating

1.04

ration

0.95

rations

0.89

rated

0.88

rent

0.76

mble

0.75

senal

0.74

secution

0.73

theless

0.72

hyde

0.72

Activations Density 0.021%

words related to evaluation or judgment

phrases and terms related to the concept of rating or evaluation

No Comments

No Known Activations