INDEX

Explanations

adjectives describing positive experiences

oai_token-act-pair · gpt-3.5-turbo

descriptions of pleasant or unpleasant experiences and feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arius

-0.68

 blindly

-0.64

aan

-0.63

ULE

-0.62

inition

-0.62

ithing

-0.61

limits

-0.61

mining

-0.61

govtrack

-0.60

rules

-0.60

POSITIVE LOGITS

ries

1.09

lihood

0.98

 pleasant

0.89

 smelling

0.86

 surprises

0.82

ness

0.81

ãĥ¼ãĥĨ

0.77

 experiences

0.77

rious

0.76

 unpleasant

0.76

Activations Density 0.031%

adjectives describing positive experiences

descriptions of pleasant or unpleasant experiences and feelings

No Comments

No Known Activations