INDEX

Explanations

terms related to governmental bodies or activities

oai_token-act-pair · gpt-3.5-turbo

mentions of government

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

omatic

-0.72

actionDate

-0.69

 Frequency

-0.69

ranging

-0.67

cheon

-0.63

colo

-0.62

iability

-0.62

 calib

-0.61

var

-0.60

ECTION

-0.60

POSITIVE LOGITS

 intervened

0.87

 tasked

0.82

 subsidized

0.81

 sanctioned

0.76

 funded

0.75

eers

0.72

 subsid

0.72

 intervene

0.71

 slapped

0.71

 launched

0.69

Activations Density 0.116%

terms related to governmental bodies or activities

mentions of government

No Comments

No Known Activations