INDEX

Explanations

references to the sports team "Rams"

oai_token-act-pair · gpt-3.5-turbo

references to the Rams football team

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

judicial

-0.79

lly

-0.74

 causal

-0.67

 coronary

-0.66

ternity

-0.66

CLASSIFIED

-0.64

 disadvant

-0.62

 testim

-0.62

 whistlebl

-0.60

 bellig

-0.59

POSITIVE LOGITS

 Rams

1.06

aic

0.96

mers

0.93

borg

0.86

istani

0.84

eco

0.84

opa

0.84

seys

0.78

oran

0.77

sburg

0.77

Activations Density 0.019%

references to the sports team "Rams"

references to the Rams football team

No Comments

No Known Activations